arXiv daily: Computer Vision and Pattern Recognition (cs.CV)

Authors:Tao Zhang, Xingye Tian, Yu Wu, Shunping Ji, Xuebo Wang, Yuan Zhang, Pengfei Wan

Abstract: Video instance segmentation (VIS) is a critical task with diverse applications, including autonomous driving and video editing. Existing methods often underperform on complex and long videos in real world, primarily due to two factors. Firstly, offline methods are limited by the tightly-coupled modeling paradigm, which treats all frames equally and disregards the interdependencies between adjacent frames. Consequently, this leads to the introduction of excessive noise during long-term temporal alignment. Secondly, online methods suffer from inadequate utilization of temporal information. To tackle these challenges, we propose a decoupling strategy for VIS by dividing it into three independent sub-tasks: segmentation, tracking, and refinement. The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement. We introduce a novel referring tracker and temporal refiner to construct the \textbf{D}ecoupled \textbf{VIS} framework (\textbf{DVIS}). DVIS achieves new SOTA performance in both VIS and VPS, surpassing the current SOTA methods by 7.3 AP and 9.6 VPQ on the OVIS and VIPSeg datasets, which are the most challenging and realistic benchmarks. Moreover, thanks to the decoupling strategy, the referring tracker and temporal refiner are super light-weight (only 1.69\% of the segmenter FLOPs), allowing for efficient training and inference on a single GPU with 11G memory. The code is available at \href{https://github.com/zhang-tao-whu/DVIS}{https://github.com/zhang-tao-whu/DVIS}.

Authors:Paul Yoo, Jiaxian Guo, Yutaka Matsuo, Shixiang Shane Gu

Abstract: Synthesizing novel view images from a few views is a challenging but practical problem. Existing methods often struggle with producing high-quality results or necessitate per-object optimization in such few-view settings due to the insufficient information provided. In this work, we explore leveraging the strong 2D priors in pre-trained diffusion models for synthesizing novel view images. 2D diffusion models, nevertheless, lack 3D awareness, leading to distorted image synthesis and compromising the identity. To address these problems, we propose DreamSparse, a framework that enables the frozen pre-trained diffusion model to generate geometry and identity-consistent novel view image. Specifically, DreamSparse incorporates a geometry module designed to capture 3D features from sparse views as a 3D prior. Subsequently, a spatial guidance model is introduced to convert these 3D feature maps into spatial information for the generative process. This information is then used to guide the pre-trained diffusion model, enabling it to generate geometrically consistent images without tuning it. Leveraging the strong image priors in the pre-trained diffusion models, DreamSparse is capable of synthesizing high-quality novel views for both object and scene-level images and generalising to open-set images. Experimental results demonstrate that our framework can effectively synthesize novel view images from sparse views and outperforms baselines in both trained and open-set category images. More results can be found on our project page: https://sites.google.com/view/dreamsparse-webpage.

Authors:Vardaan Pahuja, AJ Piergiovanni, Anelia Angelova

Abstract: Building joint representations across images and text is an essential step for tasks such as Visual Question Answering and Video Question Answering. In this work, we find that the representations must not only jointly capture features from both modalities but should also be diverse for better generalization performance. To this end, we propose joint vision-language representation learning by diversifying the tokenization learning process, enabling tokens that are sufficiently disentangled from each other to be learned from both modalities. We observe that our approach outperforms the baseline models in a majority of settings and is competitive with state-of-the-art methods.

Authors:Wenfeng Yan, Shaoxiang Chen, Zuxuan Wu, Yu-Gang Jiang

Abstract: The task of moment localization is to localize a temporal moment in an untrimmed video for a given natural language query. Since untrimmed video contains highly redundant contents, the quality of the query is crucial for accurately localizing moments, i.e., the query should provide precise information about the target moment so that the localization model can understand what to look for in the videos. However, the natural language queries in current datasets may not be easy to understand for existing models. For example, the Ego4D dataset uses question sentences as the query to describe relatively complex moments. While being natural and straightforward for humans, understanding such question sentences are challenging for mainstream moment localization models like 2D-TAN. Inspired by the recent success of large language models, especially their ability of understanding and generating complex natural language contents, in this extended abstract, we make early attempts at reformulating the moment queries into a set of instructions using large language models and making them more friendly to the localization models.

Authors:Yihan Wen, Jialu Sui, Xianping Ma, Wendi Liang, Xiaokang Zhang, Man-On Pun

Abstract: Deep learning (DL) approaches based on CNN-purely or Transformer networks have demonstrated promising results in bitemporal change detection (CD). However, their performance is limited by insufficient contextual information aggregation, as they struggle to fully capture the implicit contextual dependency relationships among feature maps at different levels. Additionally, researchers have utilized pre-trained denoising diffusion probabilistic models (DDPMs) for training lightweight CD classifiers. Nevertheless, training a DDPM to generate intricately detailed, multi-channel remote sensing images requires months of training time and a substantial volume of unlabeled remote sensing datasets, making it significantly more complex than generating a single-channel change map. To overcome these challenges, we propose a novel end-to-end DDPM-based model architecture called change-aware diffusion model (CADM), which can be trained using a limited annotated dataset quickly. Furthermore, we introduce dynamic difference conditional encoding to enhance step-wise regional attention in DDPM for bitemporal images in CD datasets. This method establishes state-adaptive conditions for each sampling step, emphasizing two main innovative points of our model: 1) its end-to-end nature and 2) difference conditional encoding. We evaluate CADM on four remote sensing CD tasks with different ground scenarios, including CDD, WHU, Levier, and GVLM. Experimental results demonstrate that CADM significantly outperforms state-of-the-art methods, indicating the generalization and effectiveness of the proposed model.

Authors:Huanzhang Dou, Pengyi Zhang, Wei Su, Yunlong Yu, Yining Lin, Xi Li

Abstract: Gait is one of the most promising biometrics that aims to identify pedestrians from their walking patterns. However, prevailing methods are susceptible to confounders, resulting in the networks hardly focusing on the regions that reflect effective walking patterns. To address this fundamental problem in gait recognition, we propose a Generative Counterfactual Intervention framework, dubbed GaitGCI, consisting of Counterfactual Intervention Learning (CIL) and Diversity-Constrained Dynamic Convolution (DCDC). CIL eliminates the impacts of confounders by maximizing the likelihood difference between factual/counterfactual attention while DCDC adaptively generates sample-wise factual/counterfactual attention to efficiently perceive the sample-wise properties. With matrix decomposition and diversity constraint, DCDC guarantees the model to be efficient and effective. Extensive experiments indicate that proposed GaitGCI: 1) could effectively focus on the discriminative and interpretable regions that reflect gait pattern; 2) is model-agnostic and could be plugged into existing models to improve performance with nearly no extra cost; 3) efficiently achieves state-of-the-art performance on arbitrary scenarios (in-the-lab and in-the-wild).

Authors:Xingxing Wei, Shiji Zhao

Abstract: Adversarial attacks have been proven to be potential threats to Deep Neural Networks (DNNs), and many methods are proposed to defend against adversarial attacks. However, while enhancing the robustness, the clean accuracy will decline to a certain extent, implying a trade-off existed between the accuracy and robustness. In this paper, we firstly empirically find an obvious distinction between standard and robust models in the filters' weight distribution of the same architecture, and then theoretically explain this phenomenon in terms of the gradient regularization, which shows this difference is an intrinsic property for DNNs, and thus a static network architecture is difficult to improve the accuracy and robustness at the same time. Secondly, based on this observation, we propose a sample-wise dynamic network architecture named Adversarial Weight-Varied Network (AW-Net), which focuses on dealing with clean and adversarial examples with a ``divide and rule" weight strategy. The AW-Net dynamically adjusts network's weights based on regulation signals generated by an adversarial detector, which is directly influenced by the input sample. Benefiting from the dynamic network architecture, clean and adversarial examples can be processed with different network weights, which provides the potentiality to enhance the accuracy and robustness simultaneously. A series of experiments demonstrate that our AW-Net is architecture-friendly to handle both clean and adversarial examples and can achieve better trade-off performance than state-of-the-art robust models.

Authors:Hefeng Wang, Jiale Cao, Rao Muhammad Anwer, Jin Xie, Fahad Shahbaz Khan, Yanwei Pang

Abstract: This paper introduces an approach, named DFormer, for universal image segmentation. The proposed DFormer views universal image segmentation task as a denoising process using a diffusion model. DFormer first adds various levels of Gaussian noise to ground-truth masks, and then learns a model to predict denoising masks from corrupted masks. Specifically, we take deep pixel-level features along with the noisy masks as inputs to generate mask features and attention masks, employing diffusion-based decoder to perform mask prediction gradually. At inference, our DFormer directly predicts the masks and corresponding categories from a set of randomly-generated masks. Extensive experiments reveal the merits of our proposed contributions on different image segmentation tasks: panoptic segmentation, instance segmentation, and semantic segmentation. Our DFormer outperforms the recent diffusion-based panoptic segmentation method Pix2Seq-D with a gain of 3.6% on MS COCO val2017 set. Further, DFormer achieves promising semantic segmentation performance outperforming the recent diffusion-based method by 2.2% on ADE20K val set. Our source code and models will be publicly on https://github.com/cp3wan/DFormer

Authors:Huanzhang Dou, Pengyi Zhang, Wei Su, Yunlong Yu, Xi Li

Abstract: Gait recognition, which aims at identifying individuals by their walking patterns, has recently drawn increasing research attention. However, gait recognition still suffers from the conflicts between the limited binary visual clues of the silhouette and numerous covariates with diverse scales, which brings challenges to the model's adaptiveness. In this paper, we address this conflict by developing a novel MetaGait that learns to learn an omni sample adaptive representation. Towards this goal, MetaGait injects meta-knowledge, which could guide the model to perceive sample-specific properties, into the calibration network of the attention mechanism to improve the adaptiveness from the omni-scale, omni-dimension, and omni-process perspectives. Specifically, we leverage the meta-knowledge across the entire process, where Meta Triple Attention and Meta Temporal Pooling are presented respectively to adaptively capture omni-scale dependency from spatial/channel/temporal dimensions simultaneously and to adaptively aggregate temporal information through integrating the merits of three complementary temporal aggregation methods. Extensive experiments demonstrate the state-of-the-art performance of the proposed MetaGait. On CASIA-B, we achieve rank-1 accuracy of 98.7%, 96.0%, and 89.3% under three conditions, respectively. On OU-MVLP, we achieve rank-1 accuracy of 92.4%.

Authors:Wenwen Yu, Mingyu Liu, Biao Yang, Enming Zhang, Deqiang Jiang, Xing Sun, Yuliang Liu, Xiang Bai

Abstract: Text recognition in the wild is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest vision and language processing are effective for scene text recognition. Yet, solving edit errors such as add, delete, or replace is still the main challenge for existing approaches. In fact, the content of the text and its audio are naturally corresponding to each other, i.e., a single character error may result in a clear different pronunciation. In this paper, we propose the AudioOCR, a simple yet effective probabilistic audio decoder for mel spectrogram sequence prediction to guide the scene text recognition, which only participates in the training phase and brings no extra cost during the inference stage. The underlying principle of AudioOCR can be easily applied to the existing approaches. Experiments using 7 previous scene text recognition methods on 12 existing regular, irregular, and occluded benchmarks demonstrate our proposed method can bring consistent improvement. More importantly, through our experimentation, we show that AudioOCR possesses a generalizability that extends to more challenging scenarios, including recognizing non-English text, out-of-vocabulary words, and text with various accents. Code will be available at https://github.com/wenwenyu/AudioOCR.

Authors:Zhishen Yang, Raj Dabre, Hideki Tanaka, Naoaki Okazaki

Abstract: In scholarly documents, figures provide a straightforward way of communicating scientific findings to readers. Automating figure caption generation helps move model understandings of scientific documents beyond text and will help authors write informative captions that facilitate communicating scientific findings. Unlike previous studies, we reframe scientific figure captioning as a knowledge-augmented image captioning task that models need to utilize knowledge embedded across modalities for caption generation. To this end, we extended the large-scale SciCap dataset~\cite{hsu-etal-2021-scicap-generating} to SciCap+ which includes mention-paragraphs (paragraphs mentioning figures) and OCR tokens. Then, we conduct experiments with the M4C-Captioner (a multimodal transformer-based model with a pointer network) as a baseline for our study. Our results indicate that mention-paragraphs serves as additional context knowledge, which significantly boosts the automatic standard image caption evaluation scores compared to the figure-only baselines. Human evaluations further reveal the challenges of generating figure captions that are informative to readers. The code and SciCap+ dataset will be publicly available at https://github.com/ZhishenYang/scientific_figure_captioning_dataset

Authors:Hanxi Li, Jingqi Wu, Hao Chen, Mingwen Wang, Chunhua Shen

Abstract: Anomaly Detection is challenging as usually only the normal samples are seen during training and the detector needs to discover anomalies on-the-fly. The recently proposed deep-learning-based approaches could somehow alleviate the problem but there is still a long way to go in obtaining an industrial-class anomaly detector for real-world applications. On the other hand, in some particular AD tasks, a few anomalous samples are labeled manually for achieving higher accuracy. However, this performance gain is at the cost of considerable annotation efforts, which can be intractable in many practical scenarios. In this work, the above two problems are addressed in a unified framework. Firstly, inspired by the success of the patch-matching-based AD algorithms, we train a sliding vision transformer over the residuals generated by a novel position-constrained patch-matching. Secondly, the conventional pixel-wise segmentation problem is cast into a block-wise classification problem. Thus the sliding transformer can attain even higher accuracy with much less annotation labor. Thirdly, to further reduce the labeling cost, we propose to label the anomalous regions using only bounding boxes. The unlabeled regions caused by the weak labels are effectively exploited using a highly-customized semi-supervised learning scheme equipped with two novel data augmentation methods. The proposed method outperforms all the state-of-the-art approaches using all the evaluation metrics in both the unsupervised and supervised scenarios. On the popular MVTec-AD dataset, our SemiREST algorithm obtains the Average Precision (AP) of 81.2% in the unsupervised condition and 84.4% AP for supervised anomaly detection. Surprisingly, with the bounding-box-based semi-supervisions, SemiREST still outperforms the SOTA methods with full supervision (83.8% AP) on MVTec-AD.

Authors:Lian Liu, Han Zhou, Jiongquan Chen, Sijing Liu, Wenlong Shi, Dong Ni, Deng-Ping Fan, Xin Yang

Abstract: Deep neural networks have been widely applied in dichotomous medical image segmentation (DMIS) of many anatomical structures in several modalities, achieving promising performance. However, existing networks tend to struggle with task-specific, heavy and complex designs to improve accuracy. They made little instructions to which feature channels would be more beneficial for segmentation, and that may be why the performance and universality of these segmentation models are hindered. In this study, we propose an instructive feature enhancement approach, namely IFE, to adaptively select feature channels with rich texture cues and strong discriminability to enhance raw features based on local curvature or global information entropy criteria. Being plug-and-play and applicable for diverse DMIS tasks, IFE encourages the model to focus on texture-rich features which are especially important for the ambiguous and challenging boundary identification, simultaneously achieving simplicity, universality, and certain interpretability. To evaluate the proposed IFE, we constructed the first large-scale DMIS dataset Cosmos55k, which contains 55,023 images from 7 modalities and 26 anatomical structures. Extensive experiments show that IFE can improve the performance of classic segmentation networks across different anatomies and modalities with only slight modifications. Code is available at https://github.com/yezi-66/IFE

Authors:Zhenhui Ye, Ziyue Jiang, Yi Ren, Jinglin Liu, Chen Zhang, Xiang Yin, Zejun Ma, Zhou Zhao

Abstract: We are interested in a novel task, namely low-resource text-to-talking avatar. Given only a few-minute-long talking person video with the audio track as the training data and arbitrary texts as the driving input, we aim to synthesize high-quality talking portrait videos corresponding to the input text. This task has broad application prospects in the digital human industry but has not been technically achieved yet due to two challenges: (1) It is challenging to mimic the timbre from out-of-domain audio for a traditional multi-speaker Text-to-Speech system. (2) It is hard to render high-fidelity and lip-synchronized talking avatars with limited training data. In this paper, we introduce Adaptive Text-to-Talking Avatar (Ada-TTA), which (1) designs a generic zero-shot multi-speaker TTS model that well disentangles the text content, timbre, and prosody; and (2) embraces recent advances in neural rendering to achieve realistic audio-driven talking face video generation. With these designs, our method overcomes the aforementioned two challenges and achieves to generate identity-preserving speech and realistic talking person video. Experiments demonstrate that our method could synthesize realistic, identity-preserving, and audio-visual synchronized talking avatar videos.

Authors:Min Yan, Qianxiong Ning, Qian Wang

Abstract: Video scene parsing incorporates temporal information, which can enhance the consistency and accuracy of predictions compared to image scene parsing. The added temporal dimension enables a more comprehensive understanding of the scene, leading to more reliable results. This paper presents the winning solution of the CVPR2023 workshop for video semantic segmentation, focusing on enhancing Spatial-Temporal correlations with contrastive loss. We also explore the influence of multi-dataset training by utilizing a label-mapping technique. And the final result is aggregating the output of the above two models. Our approach achieves 65.95% mIoU performance on the VSPW dataset, ranked 1st place on the VSPW challenge at CVPR 2023.

Authors:Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, Yandong Guo, Lei Zhang

Abstract: We present the Recognize Anything Model (RAM): a strong foundation model for image tagging. RAM can recognize any common category with high accuracy. RAM introduces a new paradigm for image tagging, leveraging large-scale image-text pairs for training instead of manual annotations. The development of RAM comprises four key steps. Firstly, annotation-free image tags are obtained at scale through automatic text semantic parsing. Subsequently, a preliminary model is trained for automatic annotation by unifying the caption and tagging tasks, supervised by the original texts and parsed tags, respectively. Thirdly, a data engine is employed to generate additional annotations and clean incorrect ones. Lastly, the model is retrained with the processed data and fine-tuned using a smaller but higher-quality dataset. We evaluate the tagging capabilities of RAM on numerous benchmarks and observe impressive zero-shot performance, significantly outperforming CLIP and BLIP. Remarkably, RAM even surpasses the fully supervised manners and exhibits competitive performance with the Google API. We are releasing the RAM at \url{https://recognize-anything.github.io/} to foster the advancements of large models in computer vision.

Authors:Fatemeh Aghaeipoor, Dorsa Asgarian, Mohammad Sabokrou

Abstract: Explainability of intelligent models has been garnering increasing attention in recent years. Of the various explainability approaches, concept-based techniques are notable for utilizing a set of human-meaningful concepts instead of focusing on individual pixels. However, there is a scarcity of methods that consistently provide both local and global explanations. Moreover, most of the methods have no offer to explain misclassification cases. To address these challenges, our study follows a straightforward yet effective approach. We propose a unified concept-based system, which inputs a number of super-pixelated images into the networks, allowing them to learn better representations of the target's objects as well as the target's concepts. This method automatically learns, scores, and extracts local and global concepts. Our experiments revealed that, in addition to enhancing performance, the models could provide deeper insights into predictions and elucidate false classifications.

Authors:Mikołaj Łysakowski, Kamil Żywanowski, Adam Banaszczyk, Michał R. Nowicki, Piotr Skrzypczyński, Sławomir K. Tadeja

Abstract: This paper introduces a software architecture for real-time object detection using machine learning (ML) in an augmented reality (AR) environment. Our approach uses the recent state-of-the-art YOLOv8 network that runs onboard on the Microsoft HoloLens 2 head-mounted display (HMD). The primary motivation behind this research is to enable the application of advanced ML models for enhanced perception and situational awareness with a wearable, hands-free AR platform. We show the image processing pipeline for the YOLOv8 model and the techniques used to make it real-time on the resource-limited edge computing platform of the headset. The experimental results demonstrate that our solution achieves real-time processing without needing offloading tasks to the cloud or any other external servers while retaining satisfactory accuracy regarding the usual mAP metric and measured qualitative performance

Authors:Honghao Fu

Abstract: To mitigate the challenges arising from partial occlusion in human pose keypoint based pedestrian detection methods , we present a novel pedestrian pose keypoint completion method called the separation and dimensionality reduction-based generative adversarial imputation networks (SDR-GAIN) . Firstly, we utilize OpenPose to estimate pedestrian poses in images. Then, we isolate the head and torso keypoints of pedestrians with incomplete keypoints due to occlusion or other factors and perform dimensionality reduction to enhance features and further unify feature distribution. Finally, we introduce two generative models based on the generative adversarial networks (GAN) framework, which incorporate Huber loss, residual structure, and L1 regularization to generate missing parts of the incomplete head and torso pose keypoints of partially occluded pedestrians, resulting in pose completion. Our experiments on MS COCO and JAAD datasets demonstrate that SDR-GAIN outperforms basic GAIN framework, interpolation methods PCHIP and MAkima, machine learning methods k-NN and MissForest in terms of pose completion task. In addition, the runtime of SDR-GAIN is approximately 0.4ms, displaying high real-time performance and significant application value in the field of autonomous driving.

Authors:Mingyang Sun, Dingkang Yang, Dongliang Kou, Yang Jiang, Weihua Shan, Zhe Yan, Lihua Zhang

Abstract: A human 3D avatar is one of the important elements in the metaverse, and the modeling effect directly affects people's visual experience. However, the human body has a complex topology and diverse details, so it is often expensive, time-consuming, and laborious to build a satisfactory model. Recent studies have proposed a novel method, implicit neural representation, which is a continuous representation method and can describe objects with arbitrary topology at arbitrary resolution. Researchers have applied implicit neural representation to human 3D avatar modeling and obtained more excellent results than traditional methods. This paper comprehensively reviews the application of implicit neural representation in human body modeling. First, we introduce three implicit representations of occupancy field, SDF, and NeRF, and make a classification of the literature investigated in this paper. Then the application of implicit modeling methods in the body, hand, and head are compared and analyzed respectively. Finally, we point out the shortcomings of current work and provide available suggestions for researchers.

Authors:Anuj Rai, Ashutosh Anshul, Ashwini Jha, Prayag Jain, Ramprakash Sharma, Somnath Dey

Abstract: The low-cost, user-friendly, and convenient nature of Automatic Fingerprint Recognition Systems (AFRS) makes them suitable for a wide range of applications. This spreading use of AFRS also makes them vulnerable to various security threats. Presentation Attack (PA) or spoofing is one of the threats which is caused by presenting a spoof of a genuine fingerprint to the sensor of AFRS. Fingerprint Presentation Attack Detection (FPAD) is a countermeasure intended to protect AFRS against fake or spoof fingerprints created using various fabrication materials. In this paper, we have proposed a Convolutional Neural Network (CNN) based technique that uses a Generative Adversarial Network (GAN) to augment the dataset with spoof samples generated from the proposed Open Patch Generator (OPG). This OPG is capable of generating realistic fingerprint samples which have no resemblance to the existing spoof fingerprint samples generated with other materials. The augmented dataset is fed to the DenseNet classifier which helps in increasing the performance of the Presentation Attack Detection (PAD) module for the various real-world attacks possible with unknown spoof materials. Experimental evaluations of the proposed approach are carried out on the Liveness Detection (LivDet) 2015, 2017, and 2019 competition databases. An overall accuracy of 96.20\%, 94.97\%, and 92.90\% has been achieved on the LivDet 2015, 2017, and 2019 databases, respectively under the LivDet protocol scenarios. The performance of the proposed PAD model is also validated in the cross-material and cross-sensor attack paradigm which further exhibits its capability to be used under real-world attack scenarios.

Authors:Haowen Wang, Zhengping Che, Mingyuan Wang, Zhiyuan Xu, Xiuquan Qiao, Mengshi Qi, Feifei Feng, Jian Tang

Abstract: The raw depth image captured by indoor depth sensors usually has an extensive range of missing depth values due to inherent limitations such as the inability to perceive transparent objects and the limited distance range. The incomplete depth map with missing values burdens many downstream vision tasks, and a rising number of depth completion methods have been proposed to alleviate this issue. While most existing methods can generate accurate dense depth maps from sparse and uniformly sampled depth maps, they are not suitable for complementing large contiguous regions of missing depth values, which is common and critical in images captured in indoor environments. To overcome these challenges, we design a novel two-branch end-to-end fusion network named RDFC-GAN, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map. The first branch employs an encoder-decoder structure, by adhering to the Manhattan world assumption and utilizing normal maps from RGB-D information as guidance, to regress the local dense depth values from the raw depth map. In the other branch, we propose an RGB-depth fusion CycleGAN to transfer the RGB image to the fine-grained textured depth map. We adopt adaptive fusion modules named W-AdaIN to propagate the features across the two branches, and we append a confidence fusion head to fuse the two outputs of the branches for the final depth map. Extensive experiments on NYU-Depth V2 and SUN RGB-D demonstrate that our proposed method clearly improves the depth completion performance, especially in a more realistic setting of indoor environments, with the help of our proposed pseudo depth maps in training.

Authors:Jianrong Wang, Yaxin Zhao, Li Liu, Tianyi Xu, Qi Li, Sen Li

Abstract: Given an audio clip and a reference face image, the goal of the talking head generation is to generate a high-fidelity talking head video. Although some audio-driven methods of generating talking head videos have made some achievements in the past, most of them only focused on lip and audio synchronization and lack the ability to reproduce the facial expressions of the target person. To this end, we propose a talking head generation model consisting of a Memory-Sharing Emotion Feature extractor (MSEF) and an Attention-Augmented Translator based on U-net (AATU). Firstly, MSEF can extract implicit emotional auxiliary features from audio to estimate more accurate emotional face landmarks.~Secondly, AATU acts as a translator between the estimated landmarks and the photo-realistic video frames. Extensive qualitative and quantitative experiments have shown the superiority of the proposed method to the previous works. Codes will be made publicly available.

Authors:Zhifan Ni, Esteve Valls Mascaró, Hyemin Ahn, Dongheui Lee

Abstract: Understanding the human-object interactions (HOIs) from a video is essential to fully comprehend a visual scene. This line of research has been addressed by detecting HOIs from images and lately from videos. However, the video-based HOI anticipation task in the third-person view remains understudied. In this paper, we design a framework to detect current HOIs and anticipate future HOIs in videos. We propose to leverage human gaze information since people often fixate on an object before interacting with it. These gaze features together with the scene contexts and the visual appearances of human-object pairs are fused through a spatio-temporal transformer. To evaluate the model in the HOI anticipation task in a multi-person scenario, we propose a set of person-wise multi-label metrics. Our model is trained and validated on the VidHOI dataset, which contains videos capturing daily life and is currently the largest video HOI dataset. Experimental results in the HOI detection task show that our approach improves the baseline by a great margin of 36.3% relatively. Moreover, we conduct an extensive ablation study to demonstrate the effectiveness of our modifications and extensions to the spatio-temporal transformer. Our code is publicly available on https://github.com/nizhf/hoi-prediction-gaze-transformer.

Authors:Aixuan Li, Yuxin Mao, Jing Zhang, Yuchao Dai

Abstract: In this paper, we present a weakly-supervised RGB-D salient object detection model via scribble supervision. Specifically, as a multimodal learning task, we focus on effective multimodal representation learning via inter-modal mutual information regularization. In particular, following the principle of disentangled representation learning, we introduce a mutual information upper bound with a mutual information minimization regularizer to encourage the disentangled representation of each modality for salient object detection. Based on our multimodal representation learning framework, we introduce an asymmetric feature extractor for our multimodal data, which is proven more effective than the conventional symmetric backbone setting. We also introduce multimodal variational auto-encoder as stochastic prediction refinement techniques, which takes pseudo labels from the first training stage as supervision and generates refined prediction. Experimental results on benchmark RGB-D salient object detection datasets verify both effectiveness of our explicit multimodal disentangled representation learning method and the stochastic prediction refinement strategy, achieving comparable performance with the state-of-the-art fully supervised models. Our code and data are available at: https://github.com/baneitixiaomai/MIRV.

Authors:Yash Turkar, Pranay Meshram, Charuvahan Adhivarahan, Karthik Dantu

Abstract: LiDAR-based mapping/reconstruction are important for various applications, but evaluating the quality of the dense maps they produce is challenging. The current methods have limitations, including the inability to capture completeness, structural information, and local variations in error. In this paper, we propose a novel point quality evaluation metric (PQM) that consists of four sub-metrics to provide a more comprehensive evaluation of point cloud quality. The completeness sub-metric evaluates the proportion of missing data, the artifact score sub-metric recognizes and characterizes artifacts, the accuracy sub-metric measures registration accuracy, and the resolution sub-metric quantifies point cloud density. Through an ablation study using a prototype dataset, we demonstrate the effectiveness of each of the sub-metrics and compare them to popular point cloud distance measures. Using three LiDAR SLAM systems to generate maps, we evaluate their output map quality and demonstrate the metrics robustness to noise and artifacts. Our implementation of PQM, datasets and detailed documentation on how to integrate with your custom dense mapping pipeline can be found at github.com/droneslab/pqm

Authors:Fusheng Hao, Fengxiang He, Yikai Wang, Fuxiang Wu, Jing Zhang, Jun Cheng, Dacheng Tao

Abstract: Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To reconcile this conflict, this paper proposes an efficient privacy-preserving learning paradigm, where images are first encrypted to become ``human-imperceptible, machine-recognizable'' via one of the two encryption strategies: (1) random shuffling to a set of equally-sized patches and (2) mixing-up sub-patches of the images. Then, minimal adaptations are made to vision transformer to enable it to learn on the encrypted images for vision tasks, including image classification and object detection. Extensive experiments on ImageNet and COCO show that the proposed paradigm achieves comparable accuracy with the competitive methods. Decrypting the encrypted images requires solving an NP-hard jigsaw puzzle or an ill-posed inverse problem, which is empirically shown intractable to be recovered by various attackers, including the powerful vision transformer-based attacker. We thus show that the proposed paradigm can ensure the encrypted images have become human-imperceptible while preserving machine-recognizable information. The code is available at \url{https://github.com/FushengHao/PrivacyPreservingML.}

Authors:Yuncheng Jiang, Zixun Zhang, Ruimao Zhang, Guanbin Li, Shuguang Cui, Zhen Li

Abstract: Accurate polyp detection is essential for assisting clinical rectal cancer diagnoses. Colonoscopy videos contain richer information than still images, making them a valuable resource for deep learning methods. Great efforts have been made to conduct video polyp detection through multi-frame temporal/spatial aggregation. However, unlike common fixed-camera video, the camera-moving scene in colonoscopy videos can cause rapid video jitters, leading to unstable training for existing video detection models. Additionally, the concealed nature of some polyps and the complex background environment further hinder the performance of existing video detectors. In this paper, we propose the \textbf{YONA} (\textbf{Y}ou \textbf{O}nly \textbf{N}eed one \textbf{A}djacent Reference-frame) method, an efficient end-to-end training framework for video polyp detection. YONA fully exploits the information of one previous adjacent frame and conducts polyp detection on the current frame without multi-frame collaborations. Specifically, for the foreground, YONA adaptively aligns the current frame's channel activation patterns with its adjacent reference frames according to their foreground similarity. For the background, YONA conducts background dynamic alignment guided by inter-frame difference to eliminate the invalid features produced by drastic spatial jitters. Moreover, YONA applies cross-frame contrastive learning during training, leveraging the ground truth bounding box to improve the model's perception of polyp and background. Quantitative and qualitative experiments on three public challenging benchmarks demonstrate that our proposed YONA outperforms previous state-of-the-art competitors by a large margin in both accuracy and speed.

Authors:Jonathan Carter, João Jorge, Bindia Venugopal, Oliver Gibson, Lionel Tarassenko

Abstract: Conventional sleep monitoring is time-consuming, expensive and uncomfortable, requiring a large number of contact sensors to be attached to the patient. Video data is commonly recorded as part of a sleep laboratory assessment. If accurate sleep staging could be achieved solely from video, this would overcome many of the problems of traditional methods. In this work we use heart rate, breathing rate and activity measures, all derived from a near-infrared video camera, to perform sleep stage classification. We use a deep transfer learning approach to overcome data scarcity, by using an existing contact-sensor dataset to learn effective representations from the heart and breathing rate time series. Using a dataset of 50 healthy volunteers, we achieve an accuracy of 73.4\% and a Cohen's kappa of 0.61 in four-class sleep stage classification, establishing a new state-of-the-art for video-based sleep staging.

Authors:Chethan Parameshwara, Alessandro Achille, Matthew Trager, Xiaolong Li, Jiawei Mo, Matthew Trager, Ashwin Swaminathan, CJ Taylor, Dheera Venkatraman, Xiaohan Fei, Stefano Soatto

Abstract: We describe a first step towards learning general-purpose visual representations of physical scenes using only image prediction as a training criterion. To do so, we first define "physical scene" and show that, even though different agents may maintain different representations of the same scene, the underlying physical scene that can be inferred is unique. Then, we show that NeRFs cannot represent the physical scene, as they lack extrapolation mechanisms. Those, however, could be provided by Diffusion Models, at least in theory. To test this hypothesis empirically, NeRFs can be combined with Diffusion Models, a process we refer to as NeRF Diffusion, used as unsupervised representations of the physical scene. Our analysis is limited to visual data, without external grounding mechanisms that can be provided by independent sensory modalities.

Authors:Carolin Schmitt, Božidar Antić, Andrei Neculai, Joo Ho Lee, Andreas Geiger

Abstract: In this paper, we propose a novel method for joint recovery of camera pose, object geometry and spatially-varying Bidirectional Reflectance Distribution Function (svBRDF) of 3D scenes that exceed object-scale and hence cannot be captured with stationary light stages. The input are high-resolution RGB-D images captured by a mobile, hand-held capture system with point lights for active illumination. Compared to previous works that jointly estimate geometry and materials from a hand-held scanner, we formulate this problem using a single objective function that can be minimized using off-the-shelf gradient-based solvers. To facilitate scalability to large numbers of observation views and optimization variables, we introduce a distributed optimization algorithm that reconstructs 2.5D keyframe-based representations of the scene. A novel multi-view consistency regularizer effectively synchronizes neighboring keyframes such that the local optimization results allow for seamless integration into a globally consistent 3D model. We provide a study on the importance of each component in our formulation and show that our method compares favorably to baselines. We further demonstrate that our method accurately reconstructs various objects and materials and allows for expansion to spatially larger scenes. We believe that this work represents a significant step towards making geometry and material estimation from hand-held scanners scalable.

Authors:Drew Linsley, Ivan F. Rodriguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret Livingstone, Thomas Serre

Abstract: One of the most impactful findings in computational neuroscience over the past decade is that the object recognition accuracy of deep neural networks (DNNs) correlates with their ability to predict neural responses to natural images in the inferotemporal (IT) cortex. This discovery supported the long-held theory that object recognition is a core objective of the visual cortex, and suggested that more accurate DNNs would serve as better models of IT neuron responses to images. Since then, deep learning has undergone a revolution of scale: billion parameter-scale DNNs trained on billions of images are rivaling or outperforming humans at visual tasks including object recognition. Have today's DNNs become more accurate at predicting IT neuron responses to images as they have grown more accurate at object recognition? Surprisingly, across three independent experiments, we find this is not the case. DNNs have become progressively worse models of IT as their accuracy has increased on ImageNet. To understand why DNNs experience this trade-off and evaluate if they are still an appropriate paradigm for modeling the visual system, we turn to recordings of IT that capture spatially resolved maps of neuronal activity elicited by natural images. These neuronal activity maps reveal that DNNs trained on ImageNet learn to rely on different visual features than those encoded by IT and that this problem worsens as their accuracy increases. We successfully resolved this issue with the neural harmonizer, a plug-and-play training routine for DNNs that aligns their learned representations with humans. Our results suggest that harmonized DNNs break the trade-off between ImageNet accuracy and neural prediction accuracy that assails current DNNs and offer a path to more accurate models of biological vision.

Authors:Effrosyni Mavroudi, Triantafyllos Afouras, Lorenzo Torresani

Abstract: In this paper we present an approach for localizing steps of procedural activities in narrated how-to videos. To deal with the scarcity of labeled data at scale, we source the step descriptions from a language knowledge base (wikiHow) containing instructional articles for a large variety of procedural tasks. Without any form of manual supervision, our model learns to temporally ground the steps of procedural articles in how-to videos by matching three modalities: frames, narrations, and step descriptions. Specifically, our method aligns steps to video by fusing information from two distinct pathways: i) {\em direct} alignment of step descriptions to frames, ii) {\em indirect} alignment obtained by composing steps-to-narrations with narrations-to-video correspondences. Notably, our approach performs global temporal grounding of all steps in an article at once by exploiting order information, and is trained with step pseudo-labels which are iteratively refined and aggressively filtered. In order to validate our model we introduce a new evaluation benchmark -- HT-Step -- obtained by manually annotating a 124-hour subset of HowTo100M\footnote{A test server is accessible at \url{https://eval.ai/web/challenges/challenge-page/2082}.} with steps sourced from wikiHow articles. Experiments on this benchmark as well as zero-shot evaluations on CrossTask demonstrate that our multi-modality alignment yields dramatic gains over several baselines and prior works. Finally, we show that our inner module for matching narration-to-video outperforms by a large margin the state of the art on the HTM-Align narration-video alignment benchmark.

Authors:Shubhankar Borse, Senthil Yogamani, Marvin Klingner, Varun Ravi, Hong Cai, Abdulaziz Almuzairee, Fatih Porikli

Abstract: Bird's-eye-view (BEV) grid is a typical representation of the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras only to perform segmentation in BEV space, which is fundamentally constrained by the absence of reliable depth information. The latest works leverage both camera and LiDAR modalities but suboptimally fuse their features using simple, concatenation-based mechanisms. In this paper, we address these problems by enhancing the alignment of the unimodal features in order to aid feature fusion, as well as enhancing the alignment between the cameras' perspective view (PV) and BEV representations. We propose X-Align, a novel end-to-end cross-modal and cross-view learning framework for BEV segmentation consisting of the following components: (i) a novel Cross-Modal Feature Alignment (X-FA) loss, (ii) an attention-based Cross-Modal Feature Fusion (X-FF) module to align multi-modal BEV features implicitly, and (iii) an auxiliary PV segmentation branch with Cross-View Segmentation Alignment (X-SA) losses to improve the PV-to-BEV transformation. We evaluate our proposed method across two commonly used benchmark datasets, i.e., nuScenes and KITTI-360. Notably, X-Align significantly outperforms the state-of-the-art by 3 absolute mIoU points on nuScenes. We also provide extensive ablation studies to demonstrate the effectiveness of the individual components.

Authors:Zehong Shen, Zhi Cen, Sida Peng, Qing Shuai, Hujun Bao, Xiaowei Zhou

Abstract: We present a novel method for recovering the absolute pose and shape of a human in a pre-scanned scene given a single image. Unlike previous methods that perform sceneaware mesh optimization, we propose to first estimate absolute position and dense scene contacts with a sparse 3D CNN, and later enhance a pretrained human mesh recovery network by cross-attention with the derived 3D scene cues. Joint learning on images and scene geometry enables our method to reduce the ambiguity caused by depth and occlusion, resulting in more reasonable global postures and contacts. Encoding scene-aware cues in the network also allows the proposed method to be optimization-free, and opens up the opportunity for real-time applications. The experiments show that the proposed network is capable of recovering accurate and physically-plausible meshes by a single forward pass and outperforms state-of-the-art methods in terms of both accuracy and speed.

Authors:Xinrong Hu, Yu-Jen Chen, Tsung-Yi Ho, Yiyu Shi

Abstract: Recent advances in denoising diffusion probabilistic models have shown great success in image synthesis tasks. While there are already works exploring the potential of this powerful tool in image semantic segmentation, its application in weakly supervised semantic segmentation (WSSS) remains relatively under-explored. Observing that conditional diffusion models (CDM) is capable of generating images subject to specific distributions, in this work, we utilize category-aware semantic information underlied in CDM to get the prediction mask of the target object with only image-level annotations. More specifically, we locate the desired class by approximating the derivative of the output of CDM w.r.t the input condition. Our method is different from previous diffusion model methods with guidance from an external classifier, which accumulates noises in the background during the reconstruction process. Our method outperforms state-of-the-art CAM and diffusion model methods on two public medical image segmentation datasets, which demonstrates that CDM is a promising tool in WSSS. Also, experiment shows our method is more time-efficient than existing diffusion model methods, making it practical for wider applications.

Authors:Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, Bharath Hariharan

Abstract: Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images. Without any additional fine-tuning or supervision on the task-specific data or annotations, DIFT is able to outperform both weakly-supervised methods and competitive off-the-shelf features in identifying semantic, geometric, and temporal correspondences. Particularly for semantic correspondence, DIFT from Stable Diffusion is able to outperform DINO and OpenCLIP by 19 and 14 accuracy points respectively on the challenging SPair-71k benchmark. It even outperforms the state-of-the-art supervised methods on 9 out of 18 categories while remaining on par for the overall performance. Project page: https://diffusionfeatures.github.io

Authors:Runnan Chen, Youquan Liu, Lingdong Kong, Nenglun Chen, Xinge Zhu, Yuexin Ma, Tongliang Liu, Wenping Wang

Abstract: Vision foundation models such as Contrastive Vision-Language Pre-training (CLIP) and Segment Anything (SAM) have demonstrated impressive zero-shot performance on image classification and segmentation tasks. However, the incorporation of CLIP and SAM for label-free scene understanding has yet to be explored. In this paper, we investigate the potential of vision foundation models in enabling networks to comprehend 2D and 3D worlds without labelled data. The primary challenge lies in effectively supervising networks under extremely noisy pseudo labels, which are generated by CLIP and further exacerbated during the propagation from the 2D to the 3D domain. To tackle these challenges, we propose a novel Cross-modality Noisy Supervision (CNS) method that leverages the strengths of CLIP and SAM to supervise 2D and 3D networks simultaneously. In particular, we introduce a prediction consistency regularization to co-train 2D and 3D networks, then further impose the networks' latent space consistency using the SAM's robust feature representation. Experiments conducted on diverse indoor and outdoor datasets demonstrate the superior performance of our method in understanding 2D and 3D open environments. Our 2D and 3D network achieves label-free semantic segmentation with 28.4% and 33.5% mIoU on ScanNet, improving 4.7% and 7.9%, respectively. And for nuScenes dataset, our performance is 26.8% with an improvement of 6%. Code will be released (https://github.com/runnanchen/Label-Free-Scene-Understanding).

Authors:Yunhan Yang, Xiaoyang Wu, Tong He, Hengshuang Zhao, Xihui Liu

Abstract: In this work, we propose SAM3D, a novel framework that is able to predict masks in 3D point clouds by leveraging the Segment-Anything Model (SAM) in RGB images without further training or finetuning. For a point cloud of a 3D scene with posed RGB images, we first predict segmentation masks of RGB images with SAM, and then project the 2D masks into the 3D points. Later, we merge the 3D masks iteratively with a bottom-up merging approach. At each step, we merge the point cloud masks of two adjacent frames with the bidirectional merging approach. In this way, the 3D masks predicted from different frames are gradually merged into the 3D masks of the whole 3D scene. Finally, we can optionally ensemble the result from our SAM3D with the over-segmentation results based on the geometric information of the 3D scenes. Our approach is experimented with ScanNet dataset and qualitative results demonstrate that our SAM3D achieves reasonable and fine-grained 3D segmentation results without any training or finetuning of SAM.

Authors:Jia Guo, Shuai Lu, Lize Jia, Weihang Zhang, Huiqi Li

Abstract: Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature representations of frozen encoder networks pre-trained on large-scale datasets, e.g. ImageNet. However, the features extracted from the encoders that are borrowed from natural image domains coincide little with the features required in the target UAD domain, such as industrial inspection and medical imaging. In this paper, we propose a novel epistemic UAD method, namely ReContrast, which optimizes the entire network to reduce biases towards the pre-trained image domain and orients the network in the target domain. We start with a feature reconstruction approach that detects anomalies from errors. Essentially, the elements of contrastive learning are elegantly embedded in feature reconstruction to prevent the network from training instability, pattern collapse, and identical shortcut, while simultaneously optimizing both the encoder and decoder on the target domain. To demonstrate our transfer ability on various image domains, we conduct extensive experiments across two popular industrial defect detection benchmarks and three medical image UAD tasks, which shows our superiority over current state-of-the-art methods.

Authors:Jiabang He, Yi Hu, Lei Wang, Xing Xu, Ning Liu, Hui Liu, Heng Tao Shen

Abstract: Numerous pre-training techniques for visual document understanding (VDU) have recently shown substantial improvements in performance across a wide range of document tasks. However, these pre-trained VDU models cannot guarantee continued success when the distribution of test data differs from the distribution of training data. In this paper, to investigate how robust existing pre-trained VDU models are to various distribution shifts, we first develop an out-of-distribution (OOD) benchmark termed Do-GOOD for the fine-Grained analysis on Document image-related tasks specifically. The Do-GOOD benchmark defines the underlying mechanisms that result in different distribution shifts and contains 9 OOD datasets covering 3 VDU related tasks, e.g., document information extraction, classification and question answering. We then evaluate the robustness and perform a fine-grained analysis of 5 latest VDU pre-trained models and 2 typical OOD generalization algorithms on these OOD datasets. Results from the experiments demonstrate that there is a significant performance gap between the in-distribution (ID) and OOD settings for document images, and that fine-grained analysis of distribution shifts can reveal the brittle nature of existing pre-trained VDU models and OOD generalization algorithms. The code and datasets for our Do-GOOD benchmark can be found at https://github.com/MAEHCM/Do-GOOD.

Authors:Chi Ding, Qingchao Zhang, Ge Wang, Xiaojing Ye, Yunmei Chen

Abstract: We propose a novel Learned Alternating Minimization Algorithm (LAMA) for dual-domain sparse-view CT image reconstruction. LAMA is naturally induced by a variational model for CT reconstruction with learnable nonsmooth nonconvex regularizers, which are parameterized as composite functions of deep networks in both image and sinogram domains. To minimize the objective of the model, we incorporate the smoothing technique and residual learning architecture into the design of LAMA. We show that LAMA substantially reduces network complexity, improves memory efficiency and reconstruction accuracy, and is provably convergent for reliable reconstructions. Extensive numerical experiments demonstrate that LAMA outperforms existing methods by a wide margin on multiple benchmark CT datasets.

Authors:Hongqiu Wang, Yueming Jin, Lei Zhu

Abstract: For robot-assisted surgery, an accurate surgical report reflects clinical operations during surgery and helps document entry tasks, post-operative analysis and follow-up treatment. It is a challenging task due to many complex and diverse interactions between instruments and tissues in the surgical scene. Although existing surgical report generation methods based on deep learning have achieved large success, they often ignore the interactive relation between tissues and instrumental tools, thereby degrading the report generation performance. This paper presents a neural network to boost surgical report generation by explicitly exploring the interactive relation between tissues and surgical instruments. We validate the effectiveness of our method on a widely-used robotic surgery benchmark dataset, and experimental results show that our network can significantly outperform existing state-of-the-art surgical report generation methods (e.g., 7.48% and 5.43% higher for BLEU-1 and ROUGE).

Authors:Zhaotong Luo, Guohang Yan, Yikang Li

Abstract: The research on extrinsic calibration between Light Detection and Ranging(LiDAR) and camera are being promoted to a more accurate, automatic and generic manner. Since deep learning has been employed in calibration, the restrictions on the scene are greatly reduced. However, data driven method has the drawback of low transfer-ability. It cannot adapt to dataset variations unless additional training is taken. With the advent of foundation model, this problem can be significantly mitigated. By using the Segment Anything Model(SAM), we propose a novel LiDAR-camera calibration method, which requires zero extra training and adapts to common scenes. With an initial guess, we opimize the extrinsic parameter by maximizing the consistency of points that are projected inside each image mask. The consistency includes three properties of the point cloud: the intensity, normal vector and categories derived from some segmentation methods. The experiments on different dataset have demonstrated the generality and comparable accuracy of our method. The code is available at https://github.com/OpenCalib/CalibAnything.

Authors:Yang Zhou, Yongjian Wu, Zihua Wang, Bingzheng Wei, Maode Lai, Jianzhong Shou, Yubo Fan, Yan Xu

Abstract: Nuclei instance segmentation on histopathology images is of great clinical value for disease analysis. Generally, fully-supervised algorithms for this task require pixel-wise manual annotations, which is especially time-consuming and laborious for the high nuclei density. To alleviate the annotation burden, we seek to solve the problem through image-level weakly supervised learning, which is underexplored for nuclei instance segmentation. Compared with most existing methods using other weak annotations (scribble, point, etc.) for nuclei instance segmentation, our method is more labor-saving. The obstacle to using image-level annotations in nuclei instance segmentation is the lack of adequate location information, leading to severe nuclei omission or overlaps. In this paper, we propose a novel image-level weakly supervised method, called cyclic learning, to solve this problem. Cyclic learning comprises a front-end classification task and a back-end semi-supervised instance segmentation task to benefit from multi-task learning (MTL). We utilize a deep learning classifier with interpretability as the front-end to convert image-level labels to sets of high-confidence pseudo masks and establish a semi-supervised architecture as the back-end to conduct nuclei instance segmentation under the supervision of these pseudo masks. Most importantly, cyclic learning is designed to circularly share knowledge between the front-end classifier and the back-end semi-supervised part, which allows the whole system to fully extract the underlying information from image-level labels and converge to a better optimum. Experiments on three datasets demonstrate the good generality of our method, which outperforms other image-level weakly supervised methods for nuclei instance segmentation, and achieves comparable performance to fully-supervised methods.

Authors:Fan Yan, Xumeng Wang, Ketian Mao, Wei Zhang, Wei Chen

Abstract: A non-fungible token (NFT) is a data unit stored on the blockchain. Nowadays, more and more investors and collectors (NFT traders), who participate in transactions of NFTs, have an urgent need to assess the performance of NFTs. However, there are two challenges for NFT traders when analyzing the performance of NFT. First, the current rarity models have flaws and are sometimes not convincing. In addition, NFT performance is dependent on multiple factors, such as images (high-dimensional data), history transactions (network), and market evolution (time series). It is difficult to take comprehensive consideration and analyze NFT performance efficiently. To address these challenges, we propose NFTVis, a visual analysis system that facilitates assessing individual NFT performance. A new NFT rarity model is proposed to quantify NFTs with images. Four well-coordinated views are designed to represent the various factors affecting the performance of the NFT. Finally, we evaluate the usefulness and effectiveness of our system using two case studies and user studies.

Authors:Sunwoo Kim, Wooseok Jang, Hyunsu Kim, Junho Kim, Yunjey Choi, Seungryong Kim, Gayeong Lee

Abstract: Recent text-driven image editing in diffusion models has shown remarkable success. However, the existing methods assume that the user's description sufficiently grounds the contexts in the source image, such as objects, background, style, and their relations. This assumption is unsuitable for real-world applications because users have to manually engineer text prompts to find optimal descriptions for different images. From the users' standpoint, prompt engineering is a labor-intensive process, and users prefer to provide a target word for editing instead of a full sentence. To address this problem, we first demonstrate the importance of a detailed text description of the source image, by dividing prompts into three categories based on the level of semantic details. Then, we propose simple yet effective methods by combining prompt generation frameworks, thereby making the prompt engineering process more user-friendly. Extensive qualitative and quantitative experiments demonstrate the importance of prompts in text-driven image editing and our method is comparable to ground-truth prompts.

Authors:Minjoon Jung, Youwon Jang, Seongho Choi, Joochan Kim, Jin-Hwa Kim, Byoung-Tak Zhang

Abstract: Video moment retrieval (VMR) aims to identify the specific moment in an untrimmed video for a given natural language query. However, this task is prone to suffer the weak visual-textual alignment problem from query ambiguity, potentially limiting further performance gains and generalization capability. Due to the complex multimodal interactions in videos, a query may not fully cover the relevant details of the corresponding moment, and the moment may contain misaligned and irrelevant frames. To tackle this problem, we propose a straightforward yet effective model, called Background-aware Moment DEtection TRansformer (BM-DETR). Given a target query and its moment, BM-DETR also takes negative queries corresponding to different moments. Specifically, our model learns to predict the target moment from the joint probability of the given query and the complement of negative queries for each candidate frame. In this way, it leverages the surrounding background to consider relative importance, improving moment sensitivity. Extensive experiments on Charades-STA and QVHighlights demonstrate the effectiveness of our model. Moreover, we show that BM-DETR can perform robustly in three challenging VMR scenarios, such as several out-of-distribution test cases, demonstrating superior generalization ability.

Authors:Kanghyeok Ko, Minhyeok Lee

Abstract: Generative Neural Radiance Fields (NeRFs) have demonstrated remarkable proficiency in synthesizing multi-view images by learning the distribution of a set of unposed images. Despite the aptitude of existing generative NeRFs in generating 3D-consistent high-quality random samples within data distribution, the creation of a 3D representation of a singular input image remains a formidable challenge. In this manuscript, we introduce ZIGNeRF, an innovative model that executes zero-shot Generative Adversarial Network (GAN) inversion for the generation of multi-view images from a single out-of-domain image. The model is underpinned by a novel inverter that maps out-of-domain images into the latent code of the generator manifold. Notably, ZIGNeRF is capable of disentangling the object from the background and executing 3D operations such as 360-degree rotation or depth and horizontal translation. The efficacy of our model is validated using multiple real-image datasets: Cats, AFHQ, CelebA, CelebA-HQ, and CompCars.

Authors:Van Binh Truong, Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Quoc Khanh Nguyen, Quoc Hung Cao

Abstract: Recent advances in Artificial Intelligence (AI) technology have promoted their use in almost every field. The growing complexity of deep neural networks (DNNs) makes it increasingly difficult and important to explain the inner workings and decisions of the network. However, most current techniques for explaining DNNs focus mainly on interpreting classification tasks. This paper proposes a method to explain the decision for any object detection model called D-CLOSE. To closely track the model's behavior, we used multiple levels of segmentation on the image and a process to combine them. We performed tests on the MS-COCO dataset with the YOLOX model, which shows that our method outperforms D-RISE and can give a better quality and less noise explanation.

Authors:Weiyue Zhao, Hao Lu, Zhiguo Cao, Xin Li

Abstract: There is a long-standing problem of repeated patterns in correspondence problems, where mismatches frequently occur because of inherent ambiguity. The unique position information associated with repeated patterns makes coordinate representations a useful supplement to appearance representations for improving feature correspondences. However, the issue of appropriate coordinate representation has remained unresolved. In this study, we demonstrate that geometric-invariant coordinate representations, such as barycentric coordinates, can significantly reduce mismatches between features. The first step is to establish a theoretical foundation for geometrically invariant coordinates. We present a seed matching and filtering network (SMFNet) that combines feature matching and consistency filtering with a coarse-to-fine matching strategy in order to acquire reliable sparse correspondences. We then introduce DEGREE, a novel anchor-to-barycentric (A2B) coordinate encoding approach, which generates multiple affine-invariant correspondence coordinates from paired images. DEGREE can be used as a plug-in with standard descriptors, feature matchers, and consistency filters to improve the matching quality. Extensive experiments in synthesized indoor and outdoor datasets demonstrate that DEGREE alleviates the problem of repeated patterns and helps achieve state-of-the-art performance. Furthermore, DEGREE also reports competitive performance in the third Image Matching Challenge at CVPR 2021. This approach offers a new perspective to alleviate the problem of repeated patterns and emphasizes the importance of choosing coordinate representations for feature correspondences.

Authors:Zhenglin Zhou, Huaxia Li, Hong Liu, Nanyang Wang, Gang Yu, Rongrong Ji

Abstract: Recently, deep learning-based facial landmark detection has achieved significant improvement. However, the semantic ambiguity problem degrades detection performance. Specifically, the semantic ambiguity causes inconsistent annotation and negatively affects the model's convergence, leading to worse accuracy and instability prediction. To solve this problem, we propose a Self-adapTive Ambiguity Reduction (STAR) loss by exploiting the properties of semantic ambiguity. We find that semantic ambiguity results in the anisotropic predicted distribution, which inspires us to use predicted distribution to represent semantic ambiguity. Based on this, we design the STAR loss that measures the anisotropism of the predicted distribution. Compared with the standard regression loss, STAR loss is encouraged to be small when the predicted distribution is anisotropic and thus adaptively mitigates the impact of semantic ambiguity. Moreover, we propose two kinds of eigenvalue restriction methods that could avoid both distribution's abnormal change and the model's premature convergence. Finally, the comprehensive experiments demonstrate that STAR loss outperforms the state-of-the-art methods on three benchmarks, i.e., COFW, 300W, and WFLW, with negligible computation overhead. Code is at https://github.com/ZhenglinZhou/STAR.

Authors:Lucas Maris, Yuki Matsuda, Keiichi Yasumoto

Abstract: Camera-based person re-identification is a heavily privacy-invading task by design, benefiting from rich visual data to match together person representations across different cameras. This high-dimensional data can then easily be used for other, perhaps less desirable, applications. We here investigate the possibility of protecting such image data against uses outside of the intended re-identification task, and introduce a differential privacy mechanism leveraging both pixelisation and colour quantisation for this purpose. We show its ability to distort images in such a way that adverse task performances are significantly reduced, while retaining high re-identification performances.

Authors:Guangyang Wu, Weijie Wu, Xiaohong Liu, Kele Xu, Tianjiao Wan, Wenyi Wang

Abstract: The misuse of real photographs with conflicting image captions in news items is an example of the out-of-context (OOC) misuse of media. In order to detect OOC media, individuals must determine the accuracy of the statement and evaluate whether the triplet (~\textit{i.e.}, the image and two captions) relates to the same event. This paper presents a novel learnable approach for detecting OOC media in ICME'23 Grand Challenge on Detecting Cheapfakes. The proposed method is based on the COSMOS structure, which assesses the coherence between an image and captions, as well as between two captions. We enhance the baseline algorithm by incorporating a Large Language Model (LLM), GPT3.5, as a feature extractor. Specifically, we propose an innovative approach to feature extraction utilizing prompt engineering to develop a robust and reliable feature extractor with GPT3.5 model. The proposed method captures the correlation between two captions and effectively integrates this module into the COSMOS baseline model, which allows for a deeper understanding of the relationship between captions. By incorporating this module, we demonstrate the potential for significant improvements in cheap-fakes detection performance. The proposed methodology holds promising implications for various applications such as natural language processing, image captioning, and text-to-image synthesis. Docker for submission is available at https://hub.docker.com/repository/docker/mulns/ acmmmcheapfakes.

Authors:Ali Alagrami, Luca Palmieri, Sinem Aslan, Marcello Pelillo, Sebastiano Vascon

Abstract: Reassembling 3D broken objects is a challenging task. A robust solution that generalizes well must deal with diverse patterns associated with different types of broken objects. We propose a method that tackles the pairwise assembly of 3D point clouds, that is agnostic on the type of object, and that relies solely on their geometrical information, without any prior information on the shape of the reconstructed object. The method receives two point clouds as input and segments them into regions using detected closed boundary contours, known as breaking curves. Possible alignment combinations of the regions of each broken object are evaluated and the best one is selected as the final alignment. Experiments were carried out both on available 3D scanned objects and on a recent benchmark for synthetic broken objects. Results show that our solution performs well in reassembling different kinds of broken objects.

Authors:David Kreuzer, Michael Munz

Abstract: The extraction of text in high quality is essential for text-based document analysis tasks like Document Classification or Named Entity Recognition. Unfortunately, this is not always ensured, as poor scan quality and the resulting artifacts lead to errors in the Optical Character Recognition (OCR) process. Current approaches using Convolutional Neural Networks show promising results for background removal tasks but fail correcting artifacts like pixelation or compression errors. For general images, Transformer backbones are getting integrated more frequently in well-known neural network structures for denoising tasks. In this work, a modified UNet structure using a Swin Transformer backbone is presented to remove typical artifacts in scanned documents. Multi-headed cross-attention skip connections are used to more selectively learn features in respective levels of abstraction. The performance of this approach is examined regarding compression errors, pixelation and random noise. An improvement in text extraction quality with a reduced error rate of up to 53.9% on the synthetic data is archived. The pretrained base-model can be easily adapted to new artifacts. The cross-attention skip connections allow to integrate textual information extracted from the encoder or in form of commands to more selectively control the models outcome. The latter is shown by means of an example application.

Authors:Yu Sun, Qian Bao, Wu Liu, Tao Mei, Michael J. Black

Abstract: Although the estimation of 3D human pose and shape (HPS) is rapidly progressing, current methods still cannot reliably estimate moving humans in global coordinates, which is critical for many applications. This is particularly challenging when the camera is also moving, entangling human and camera motion. To address these issues, we adopt a novel 5D representation (space, time, and identity) that enables end-to-end reasoning about people in scenes. Our method, called TRACE, introduces several novel architectural components. Most importantly, it uses two new "maps" to reason about the 3D trajectory of people over time in camera, and world, coordinates. An additional memory unit enables persistent tracking of people even during long occlusions. TRACE is the first one-stage method to jointly recover and track 3D humans in global coordinates from dynamic cameras. By training it end-to-end, and using full image information, TRACE achieves state-of-the-art performance on tracking and HPS benchmarks. The code and dataset are released for research purposes.

Authors:Wenwen Tong, Chonghao Sima, Tai Wang, Silei Wu, Hanming Deng, Li Chen, Yi Gu, Lewei Lu, Ping Luo, Dahua Lin, Hongyang Li

Abstract: Human driver can easily describe the complex traffic scene by visual system. Such an ability of precise perception is essential for driver's planning. To achieve this, a geometry-aware representation that quantizes the physical 3D scene into structured grid map with semantic labels per cell, termed as 3D Occupancy, would be desirable. Compared to the form of bounding box, a key insight behind occupancy is that it could capture the fine-grained details of critical obstacles in the scene, and thereby facilitate subsequent tasks. Prior or concurrent literature mainly concentrate on a single scene completion task, where we might argue that the potential of this occupancy representation might obsess broader impact. In this paper, we propose OccNet, a multi-view vision-centric pipeline with a cascade and temporal voxel decoder to reconstruct 3D occupancy. At the core of OccNet is a general occupancy embedding to represent 3D physical world. Such a descriptor could be applied towards a wide span of driving tasks, including detection, segmentation and planning. To validate the effectiveness of this new representation and our proposed algorithm, we propose OpenOcc, the first dense high-quality 3D occupancy benchmark built on top of nuScenes. Empirical experiments show that there are evident performance gain across multiple tasks, e.g., motion planning could witness a collision rate reduction by 15%-58%, demonstrating the superiority of our method.

Authors:Chengchao Shen, Jianzhong Chen, Shu Wang, Hulin Kuang, Jin Liu, Jianxin Wang

Abstract: Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. However, there are still a mass of appearance similarities between positive pair constructed by the existing methods, which inhibits the further representation improvement. In this paper, we propose a novel asymmetric patch sampling strategy for contrastive learning, to further boost the appearance asymmetry for better representations. Specifically, dual patch sampling strategies are applied to the given image, to obtain asymmetric positive pairs. First, sparse patch sampling is conducted to obtain the first view, which reduces spatial redundancy of image and allows a more asymmetric view. Second, a selective patch sampling is proposed to construct another view with large appearance discrepancy relative to the first one. Due to the inappreciable appearance similarity between positive pair, the trained model is encouraged to capture the similarity on semantics, instead of low-level ones. Experimental results demonstrate that our proposed method significantly outperforms the existing self-supervised methods on both ImageNet-1K and CIFAR dataset, e.g., 2.5% finetune accuracy improvement on CIFAR100. Furthermore, our method achieves state-of-the-art performance on downstream tasks, object detection and instance segmentation on COCO.Additionally, compared to other self-supervised methods, our method is more efficient on both memory and computation during training. The source code is available at https://github.com/visresearch/aps.

Authors:Nikolay Patakin, Mikhail Romanov, Anna Vorontsova, Mikhail Artemyev, Anton Konushin

Abstract: Nowadays, robotics, AR, and 3D modeling applications attract considerable attention to single-view depth estimation (SVDE) as it allows estimating scene geometry from a single RGB image. Recent works have demonstrated that the accuracy of an SVDE method hugely depends on the diversity and volume of the training data. However, RGB-D datasets obtained via depth capturing or 3D reconstruction are typically small, synthetic datasets are not photorealistic enough, and all these datasets lack diversity. The large-scale and diverse data can be sourced from stereo images or stereo videos from the web. Typically being uncalibrated, stereo data provides disparities up to unknown shift (geometrically incomplete data), so stereo-trained SVDE methods cannot recover 3D geometry. It was recently shown that the distorted point clouds obtained with a stereo-trained SVDE method can be corrected with additional point cloud modules (PCM) separately trained on the geometrically complete data. On the contrary, we propose GP$^{2}$, General-Purpose and Geometry-Preserving training scheme, and show that conventional SVDE models can learn correct shifts themselves without any post-processing, benefiting from using stereo data even in the geometry-preserving setting. Through experiments on different dataset mixtures, we prove that GP$^{2}$-trained models outperform methods relying on PCM in both accuracy and speed, and report the state-of-the-art results in the general-purpose geometry-preserving SVDE. Moreover, we show that SVDE models can learn to predict geometrically correct depth even when geometrically complete data comprises the minor part of the training set.

Authors:Praveen Kandula, Maitreya Suin, A. N. Rajagopalan

Abstract: Supervised networks address the task of low-light enhancement using paired images. However, collecting a wide variety of low-light/clean paired images is tedious as the scene needs to remain static during imaging. In this paper, we propose an unsupervised low-light enhancement network using contextguided illumination-adaptive norm (CIN). Inspired by coarse to fine methods, we propose to address this task in two stages. In stage-I, a pixel amplifier module (PAM) is used to generate a coarse estimate with an overall improvement in visibility and aesthetic quality. Stage-II further enhances the saturated dark pixels and scene properties of the image using CIN. Different ablation studies show the importance of PAM and CIN in improving the visible quality of the image. Next, we propose a region-adaptive single input multiple output (SIMO) model that can generate multiple enhanced images from a single lowlight image. The objective of SIMO is to let users choose the image of their liking from a pool of enhanced images. Human subjective analysis of SIMO results shows that the distribution of preferred images varies, endorsing the importance of SIMO-type models. Lastly, we propose a low-light road scene (LLRS) dataset having an unpaired collection of low-light and clean scenes. Unlike existing datasets, the clean and low-light scenes in LLRS are real and captured using fixed camera settings. Exhaustive comparisons on publicly available datasets, and the proposed dataset reveal that the results of our model outperform prior art quantitatively and qualitatively.

Authors:Shuyu Yang, Yinan Zhou, Yaxiong Wang, Yujiao Wu, Li Zhu, Zhedong Zheng

Abstract: In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 times larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.60%, +7.39%, and +15.90% [email protected] accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively.

Authors:Tianyuan Yao, Francois Rheault, Leon Y Cai, Vishwesh nath, Zuhayr Asad, Nancy Newlin, Can Cui, Ruining Deng, Karthik Ramadass, Andrea Shafer, Susan Resnick, Kurt Schilling, Bennett A. Landman, Yuankai Huo

Abstract: Diffusion-weighted magnetic resonance imaging (DW-MRI) is a critical imaging method for capturing and modeling tissue microarchitecture at a millimeter scale. A common practice to model the measured DW-MRI signal is via fiber orientation distribution function (fODF). This function is the essential first step for the downstream tractography and connectivity analyses. With recent advantages in data sharing, large-scale multi-site DW-MRI datasets are being made available for multi-site studies. However, measurement variabilities (e.g., inter- and intra-site variability, hardware performance, and sequence design) are inevitable during the acquisition of DW-MRI. Most existing model-based methods (e.g., constrained spherical deconvolution (CSD)) and learning based methods (e.g., deep learning (DL)) do not explicitly consider such variabilities in fODF modeling, which consequently leads to inferior performance on multi-site and/or longitudinal diffusion studies. In this paper, we propose a novel data-driven deep constrained spherical deconvolution method to explicitly constrain the scan-rescan variabilities for a more reproducible and robust estimation of brain microstructure from repeated DW-MRI scans. Specifically, the proposed method introduces a new 3D volumetric scanner-invariant regularization scheme during the fODF estimation. We study the Human Connectome Project (HCP) young adults test-retest group as well as the MASiVar dataset (with inter- and intra-site scan/rescan data). The Baltimore Longitudinal Study of Aging (BLSA) dataset is employed for external validation. From the experimental results, the proposed data-driven framework outperforms the existing benchmarks in repeated fODF estimation. The proposed method is assessing the downstream connectivity analysis and shows increased performance in distinguishing subjects with different biomarkers.

Authors:Shaoxu Li

Abstract: We propose a method for synthesizing edited photo-realistic digital avatars with text instructions. Given a short monocular RGB video and text instructions, our method uses an image-conditioned diffusion model to edit one head image and uses the video stylization method to accomplish the editing of other head images. Through iterative training and update (three times or more), our method synthesizes edited photo-realistic animatable 3D neural head avatars with a deformable neural radiance field head synthesis method. In quantitative and qualitative studies on various subjects, our method outperforms state-of-the-art methods.

Authors:Praveen Kandula, A. N. Rajagopalan

Abstract: Several supervised networks exist that remove haze information from underwater images using paired datasets and pixel-wise loss functions. However, training these networks requires large amounts of paired data which is cumbersome, complex and time-consuming. Also, directly using adversarial and cycle consistency loss functions for unsupervised learning is inaccurate as the underlying mapping from clean to underwater images is one-to-many, resulting in an inaccurate constraint on the cycle consistency loss. To address these issues, we propose a new method to remove haze from underwater images using unpaired data. Our model disentangles haze and content information from underwater images using a Haze Disentanglement Network (HDN). The disentangled content is used by a restoration network to generate a clean image using adversarial losses. The disentangled haze is then used as a guide for underwater image regeneration resulting in a strong constraint on cycle consistency loss and improved performance gains. Different ablation studies show that the haze and content from underwater images are effectively separated. Exhaustive experiments reveal that accurate cycle consistency constraint and the proposed network architecture play an important role in yielding enhanced results. Experiments on UFO-120, UWNet, UWScenes, and UIEB underwater datasets indicate that the results of our method outperform prior art both visually and quantitatively.

Authors:Praveen Kandula, A. N. Rajagopalan

Abstract: Satellite images are typically subject to multiple distortions. Different factors affect the quality of satellite images, including changes in atmosphere, surface reflectance, sun illumination, viewing geometries etc., limiting its application to downstream tasks. In supervised networks, the availability of paired datasets is a strong assumption. Consequently, many unsupervised algorithms have been proposed to address this problem. These methods synthetically generate a large dataset of degraded images using image formation models. A neural network is then trained with an adversarial loss to discriminate between images from distorted and clean domains. However, these methods yield suboptimal performance when tested on real images that do not necessarily conform to the generation mechanism. Also, they require a large amount of training data and are rendered unsuitable when only a few images are available. We propose a distortion disentanglement and knowledge distillation framework for satellite image restoration to address these important issues. Our algorithm requires only two images: the distorted satellite image to be restored and a reference image with similar semantics. Specifically, we first propose a mechanism to disentangle distortion. This enables us to generate images with varying degrees of distortion using the disentangled distortion and the reference image. We then propose the use of knowledge distillation to train a restoration network using the generated image pairs. As a final step, the distorted image is passed through the restoration network to get the final output. Ablation studies show that our proposed mechanism successfully disentangles distortion.

Authors:Simon Lepage, Jérémie Mary, David Picard

Abstract: This paper presents a new approach to image similarity search in the context of fashion, a domain with inherent ambiguity due to the multiple ways in which images can be considered similar. We introduce the concept of Referred Visual Search (RVS), where users provide additional information to define the desired similarity. We present a new dataset, LAION-RVS-Fashion, consisting of 272K fashion products with 842K images extracted from LAION, designed explicitly for this task. We then propose an innovative method for learning conditional embeddings using weakly-supervised training, achieving a 6% increase in Recall at one ([email protected]) against a gallery with 2M distractors, compared to classical approaches based on explicit attention and filtering. The proposed method demonstrates robustness, maintaining similar [email protected] when dealing with 2.5 times as many distractors as the baseline methods. We believe this is a step forward in the emerging field of Referred Visual Search both in terms of accessible data and approach. Code, data and models are available at https://www.github.com/Simon-Lepage/CondViT-LRVSF .

Authors:Hendrik Hachmann, Bodo Rosenhahn

Abstract: In this work, we present a marker-based multi-view spine tracking method that is specifically adjusted to the requirements for movements in sports. A maximal focus is on the accurate detection of markers and fast usage of the system. For this task, we take advantage of the prior knowledge of the arrangement of dots in perforated kinesiology tape. We detect the tape and its dots using a Mask R-CNN and a blob detector. Here, we can focus on detection only while skipping any image-based feature encoding or matching. We conduct a reasoning in 3D by a linear program and Markov random fields, in which the structure of the kinesiology tape is modeled and the shape of the spine is optimized. In comparison to state-of-the-art systems, we demonstrate that our system achieves high precision and marker density, is robust against occlusions, and capable of capturing fast movements.

Authors:Di You, Andreas Floros, Pier Luigi Dragotti

Abstract: Recently it has been shown that using diffusion models for inverse problems can lead to remarkable results. However, these approaches require a closed-form expression of the degradation model and can not support complex degradations. To overcome this limitation, we propose a method (INDigo) that combines invertible neural networks (INN) and diffusion models for general inverse problems. Specifically, we train the forward process of INN to simulate an arbitrary degradation process and use the inverse as a reconstruction process. During the diffusion sampling process, we impose an additional data-consistency step that minimizes the distance between the intermediate result and the INN-optimized result at every iteration, where the INN-optimized image is composed of the coarse information given by the observed degraded image and the details generated by the diffusion process. With the help of INN, our algorithm effectively estimates the details lost in the degradation process and is no longer limited by the requirement of knowing the closed-form expression of the degradation model. Experiments demonstrate that our algorithm obtains competitive results compared with recently leading methods both quantitatively and visually. Moreover, our algorithm performs well on more complex degradation models and real-world low-quality images.

Authors:Hendrik Hachmann, Bodo Rosenhahn

Abstract: Deep learning-based alpha matting showed tremendous improvements in recent years, yet, feature film production studios still rely on classical chroma keying including costly post-production steps. This perceived discrepancy can be explained by some missing links necessary for production which are currently not adequately addressed in the alpha matting community, in particular foreground color estimation or color spill compensation. We propose a neural network-based temporal multi-backdrop production system that combines beneficial features from chroma keying and alpha matting. Given two consecutive frames with different background colors, our one-encoder-dual-decoder network predicts foreground colors and alpha values using a patch-based overlap-blend approach. The system is able to handle imprecise backdrops, dynamic cameras, and dynamic foregrounds and has no restrictions on foreground colors. We compare our method to state-of-the-art algorithms using benchmark datasets and a video sequence captured by a demonstrator setup. We verify that a dual backdrop input is superior to the usually applied trimap-based approach. In addition, the proposed studio set is actor friendly, and produces high-quality, temporal consistent alpha and color estimations that include a superior color spill compensation.

Authors:Thomas Walker, Octave Mariotti, Amir Vaxman, Hakan Bilen

Abstract: We introduce Explicit Neural Surfaces (ENS), an efficient surface reconstruction method that learns an explicitly defined continuous surface from multiple views. We use a series of neural deformation fields to progressively transform a continuous input surface to a target shape. By sampling meshes as discrete surface proxies, we train the deformation fields through efficient differentiable rasterization, and attain a mesh-independent and smooth surface representation. By using Laplace-Beltrami eigenfunctions as an intrinsic positional encoding alongside standard extrinsic Fourier features, our approach can capture fine surface details. ENS trains 1 to 2 orders of magnitude faster and can extract meshes of higher quality compared to implicit representations, whilst maintaining competitive surface reconstruction performance and real-time capabilities. Finally, we apply our approach to learn a collection of objects in a single model, and achieve disentangled interpolations between different shapes, their surface details, and textures.

Authors:Shubham Negi, Deepika Sharma, Adarsh Kumar Kosta, Kaushik Roy

Abstract: Event-based cameras offer a low-power alternative to frame-based cameras for capturing high-speed motion and high dynamic range scenes. They provide asynchronous streams of sparse events. Spiking Neural Networks (SNNs) with their asynchronous event-driven compute, show great potential for extracting the spatio-temporal features from these event streams. In contrast, the standard Analog Neural Networks (ANNs1) fail to process event data effectively. However, training SNNs is difficult due to additional trainable parameters (thresholds and leaks), vanishing spikes at deeper layers, non-differentiable binary activation function etc. Moreover, an additional data structure "membrane potential" responsible for keeping track of temporal information, must be fetched and updated at every timestep in SNNs. To overcome these, we propose a novel SNN-ANN hybrid architecture that combines the strengths of both. Specifically, we leverage the asynchronous compute capabilities of SNN layers to effectively extract the input temporal information. While the ANN layers offer trouble-free training and implementation on standard machine learning hardware such as GPUs. We provide extensive experimental analysis for assigning each layer to be spiking or analog in nature, leading to a network configuration optimized for performance and ease of training. We evaluate our hybrid architectures for optical flow estimation using event-data on DSEC-flow and Mutli-Vehicle Stereo Event-Camera (MVSEC) datasets. The results indicate that our configured hybrid architectures outperform the state-of-the-art ANN-only, SNN-only and past hybrid architectures both in terms of accuracy and efficiency. Specifically, our hybrid architecture exhibit a 31% and 24.8% lower average endpoint error (AEE) at 2.1x and 3.1x lower energy, compared to an SNN-only architecture on DSEC and MVSEC datasets, respectively.

Authors:AKM Shahariar Azad Rabby, Chengcui Zhang

Abstract: Neural rendering combines ideas from classical computer graphics and machine learning to synthesize images from real-world observations. NeRF, short for Neural Radiance Fields, is a recent innovation that uses AI algorithms to create 3D objects from 2D images. By leveraging an interpolation approach, NeRF can produce new 3D reconstructed views of complicated scenes. Rather than directly restoring the whole 3D scene geometry, NeRF generates a volumetric representation called a ``radiance field,'' which is capable of creating color and density for every point within the relevant 3D space. The broad appeal and notoriety of NeRF make it imperative to examine the existing research on the topic comprehensively. While previous surveys on 3D rendering have primarily focused on traditional computer vision-based or deep learning-based approaches, only a handful of them discuss the potential of NeRF. However, such surveys have predominantly focused on NeRF's early contributions and have not explored its full potential. NeRF is a relatively new technique continuously being investigated for its capabilities and limitations. This survey reviews recent advances in NeRF and categorizes them according to their architectural designs, especially in the field of novel view synthesis.

Authors:Eduarda Caldeira, Pedro C. Neto, Tiago Gonçalves, Naser Damer, Ana F. Sequeira, Jaime S. Cardoso

Abstract: Morphing attacks keep threatening biometric systems, especially face recognition systems. Over time they have become simpler to perform and more realistic, as such, the usage of deep learning systems to detect these attacks has grown. At the same time, there is a constant concern regarding the lack of interpretability of deep learning models. Balancing performance and interpretability has been a difficult task for scientists. However, by leveraging domain information and proving some constraints, we have been able to develop IDistill, an interpretable method with state-of-the-art performance that provides information on both the identity separation on morph samples and their contribution to the final prediction. The domain information is learnt by an autoencoder and distilled to a classifier system in order to teach it to separate identity information. When compared to other methods in the literature it outperforms them in three out of five databases and is competitive in the remaining.

Authors:Yu-hsuan Chen, Levent Burak Kara, Jonathan Cagan

Abstract: Incorporating style-related objectives into shape design has been centrally important to maximize product appeal. However, stylistic features such as aesthetics and semantic attributes are hard to codify even for experts. As such, algorithmic style capture and reuse have not fully benefited from automated data-driven methodologies due to the challenging nature of design describability. This paper proposes an AI-driven method to fully automate the discovery of brand-related features. Our approach introduces BIGNet, a two-tier Brand Identification Graph Neural Network (GNN) to classify and analyze scalar vector graphics (SVG). First, to tackle the scarcity of vectorized product images, this research proposes two data acquisition workflows: parametric modeling from small curve-based datasets, and vectorization from large pixel-based datasets. Secondly, this study constructs a novel hierarchical GNN architecture to learn from both SVG's curve-level and chunk-level parameters. In the first case study, BIGNet not only classifies phone brands but also captures brand-related features across multiple scales, such as the location of the lens, the height-width ratio, and the screen-frame gap, as confirmed by AI evaluation. In the second study, this paper showcases the generalizability of BIGNet learning from a vectorized car image dataset and validates the consistency and robustness of its predictions given four scenarios. The results match the difference commonly observed in luxury vs. economy brands in the automobile market. Finally, this paper also visualizes the activation maps generated from a convolutional neural network and shows BIGNet's advantage of being a more human-friendly, explainable, and explicit style-capturing agent. Code and dataset can be found on Github: 1. Phone case study: github.com/parksandrecfan/bignet-phone 2. Car case study: github.com/parksandrecfan/bignet-car

Authors:Ayodeji Ijishakin, Ahmed Abdulaal, Adamos Hadjivasiliou, Sophie Martin, James Cole

Abstract: In visual object classification, humans often justify their choices by comparing objects to prototypical examples within that class. We may therefore increase the interpretability of deep learning models by imbuing them with a similar style of reasoning. In this work, we apply this principle by classifying Alzheimer's Disease based on the similarity of images to training examples within the latent space. We use a contrastive loss combined with a diffusion autoencoder backbone, to produce a semantically meaningful latent space, such that neighbouring latents have similar image-level features. We achieve a classification accuracy comparable to black box approaches on a dataset of 2D MRI images, whilst producing human interpretable model explanations. Therefore, this work stands as a contribution to the pertinent development of accurate and interpretable deep learning within medical imaging.

Authors:Xiao Han, Yukang Cao, Kai Han, Xiatian Zhu, Jiankang Deng, Yi-Zhe Song, Tao Xiang, Kwan-Yee K. Wong

Abstract: Recently, text-guided 3D generative methods have made remarkable advancements in producing high-quality textures and geometry, capitalizing on the proliferation of large vision-language and image diffusion models. However, existing methods still struggle to create high-fidelity 3D head avatars in two aspects: (1) They rely mostly on a pre-trained text-to-image diffusion model whilst missing the necessary 3D awareness and head priors. This makes them prone to inconsistency and geometric distortions in the generated avatars. (2) They fall short in fine-grained editing. This is primarily due to the inherited limitations from the pre-trained 2D image diffusion models, which become more pronounced when it comes to 3D head avatars. In this work, we address these challenges by introducing a versatile coarse-to-fine pipeline dubbed HeadSculpt for crafting (i.e., generating and editing) 3D head avatars from textual prompts. Specifically, we first equip the diffusion model with 3D awareness by leveraging landmark-based control and a learned textual embedding representing the back view appearance of heads, enabling 3D-consistent head avatar generations. We further propose a novel identity-aware editing score distillation strategy to optimize a textured mesh with a high-resolution differentiable rendering technique. This enables identity preservation while following the editing instruction. We showcase HeadSculpt's superior fidelity and editing capabilities through comprehensive experiments and comparisons with existing methods.

Authors:Yu-Hsuan Ho, Cheng-Chun Lee, Nicholas D. Diaz, Samuel D. Brody, Ali Mostafavi

Abstract: We propose an automated lowest floor elevation (LFE) estimation algorithm based on computer vision techniques to leverage the latent information in street view images. Flood depth-damage models use a combination of LFE and flood depth for determining flood risk and extent of damage to properties. We used image segmentation for detecting door bottoms and roadside edges from Google Street View images. The characteristic of equirectangular projection with constant spacing representation of horizontal and vertical angles allows extraction of the pitch angle from the camera to the door bottom. The depth from the camera to the door bottom was obtained from the depthmap paired with the Google Street View image. LFEs were calculated from the pitch angle and the depth. The testbed for application of the proposed method is Meyerland (Harris County, Texas). The results show that the proposed method achieved mean absolute error of 0.190 m (1.18 %) in estimating LFE. The height difference between the street and the lowest floor (HDSL) was estimated to provide information for flood damage estimation. The proposed automatic LFE estimation algorithm using Street View images and image segmentation provides a rapid and cost-effective method for LFE estimation compared with the surveys using total station theodolite and unmanned aerial systems. By obtaining more accurate and up-to-date LFE data using the proposed method, city planners, emergency planners and insurance companies could make a more precise estimation of flood damage.

Authors:Michael P. J. Camilleri, Rasneer S. Bains, Christopher K. I. Williams

Abstract: Behavioural experiments often happen in specialised arenas, but this may confound the analysis. To address this issue, we provide tools to study mice in the homecage environment, equipping biologists with the possibility to capture the temporal aspect of the individual's behaviour and model the interaction and interdependence between cage-mates with minimal human intervention. We develop the Activity Labelling Module (ALM) to automatically classify mouse behaviour from video, and a novel Group Behaviour Model (GBM) for summarising their joint behaviour across cages, using a permutation matrix to match the mouse identities in each cage to the model. We also release two datasets, ABODe for training behaviour classifiers and IMADGE for modelling behaviour.

Authors:Andrew F. Luo, Margaret M. Henderson, Leila Wehbe, Michael J. Tarr

Abstract: A long standing goal in neuroscience has been to elucidate the functional organization of the brain. Within higher visual cortex, functional accounts have remained relatively coarse, focusing on regions of interest (ROIs) and taking the form of selectivity for broad categories such as faces, places, bodies, food, or words. Because the identification of such ROIs has typically relied on manually assembled stimulus sets consisting of isolated objects in non-ecological contexts, exploring functional organization without robust a priori hypotheses has been challenging. To overcome these limitations, we introduce a data-driven approach in which we synthesize images predicted to activate a given brain region using paired natural images and fMRI recordings, bypassing the need for category-specific stimuli. Our approach -- Brain Diffusion for Visual Exploration ("BrainDiVE") -- builds on recent generative methods by combining large-scale diffusion models with brain-guided image synthesis. Validating our method, we demonstrate the ability to synthesize preferred images with appropriate semantic specificity for well-characterized category-selective ROIs. We then show that BrainDiVE can characterize differences between ROIs selective for the same high-level category. Finally we identify novel functional subdivisions within these ROIs, validated with behavioral data. These results advance our understanding of the fine-grained functional organization of human visual cortex, and provide well-specified constraints for further examination of cortical organization using hypothesis-driven methods.

Authors:Zhaoshuo Li, Thomas Müller, Alex Evans, Russell H. Taylor, Mathias Unberath, Ming-Yu Liu, Chen-Hsuan Lin

Abstract: Neural surface reconstruction has been shown to be powerful for recovering dense 3D surfaces via image-based neural rendering. However, current methods struggle to recover detailed structures of real-world scenes. To address the issue, we present Neuralangelo, which combines the representation power of multi-resolution 3D hash grids with neural surface rendering. Two key ingredients enable our approach: (1) numerical gradients for computing higher-order derivatives as a smoothing operation and (2) coarse-to-fine optimization on the hash grids controlling different levels of details. Even without auxiliary inputs such as depth, Neuralangelo can effectively recover dense 3D surface structures from multi-view images with fidelity significantly surpassing previous methods, enabling detailed large-scale scene reconstruction from RGB video captures.

Authors:Edward C. Williams, Grace Su, Sandra R. Schloen, Miller C. Prosser, Susanne Paulus, Sanjay Krishnan

Abstract: Twenty-five hundred years ago, the paperwork of the Achaemenid Empire was recorded on clay tablets. In 1933, archaeologists from the University of Chicago's Oriental Institute (OI) found tens of thousands of these tablets and fragments during the excavation of Persepolis. Many of these tablets have been painstakingly photographed and annotated by expert cuneiformists, and now provide a rich dataset consisting of over 5,000 annotated tablet images and 100,000 cuneiform sign bounding boxes. We leverage this dataset to develop DeepScribe, a modular computer vision pipeline capable of localizing cuneiform signs and providing suggestions for the identity of each sign. We investigate the difficulty of learning subtasks relevant to cuneiform tablet transcription on ground-truth data, finding that a RetinaNet object detector can achieve a localization mAP of 0.78 and a ResNet classifier can achieve a top-5 sign classification accuracy of 0.89. The end-to-end pipeline achieves a top-5 classification accuracy of 0.80. As part of the classification module, DeepScribe groups cuneiform signs into morphological clusters. We consider how this automatic clustering approach differs from the organization of standard, printed sign lists and what we may learn from it. These components, trained individually, are sufficient to produce a system that can analyze photos of cuneiform tablets from the Achaemenid period and provide useful transliteration suggestions to researchers. We evaluate the model's end-to-end performance on locating and classifying signs, providing a roadmap to a linguistically-aware transliteration system, then consider the model's potential utility when applied to other periods of cuneiform writing.

Authors:Hossein Aboutalebi, Daniel Mao, Carol Xu, Alexander Wong

Abstract: The tremendous recent advances in generative artificial intelligence techniques have led to significant successes and promise in a wide range of different applications ranging from conversational agents and textual content generation to voice and visual synthesis. Amid the rise in generative AI and its increasing widespread adoption, there has been significant growing concern over the use of generative AI for malicious purposes. In the realm of visual content synthesis using generative AI, key areas of significant concern has been image forgery (e.g., generation of images containing or derived from copyright content), and data poisoning (i.e., generation of adversarially contaminated images). Motivated to address these key concerns to encourage responsible generative AI, we introduce the DeepfakeArt Challenge, a large-scale challenge benchmark dataset designed specifically to aid in the building of machine learning algorithms for generative AI art forgery and data poisoning detection. Comprising of over 32,000 records across a variety of generative forgery and data poisoning techniques, each entry consists of a pair of images that are either forgeries / adversarially contaminated or not. Each of the generated images in the DeepfakeArt Challenge benchmark dataset has been quality checked in a comprehensive manner. The DeepfakeArt Challenge is a core part of GenAI4Good, a global open source initiative for accelerating machine learning for promoting responsible creation and deployment of generative AI for good.

Authors:Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa

Abstract: We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection. Few-shot OOD detection aims to detect OOD images from classes that are unseen during training using only a few labeled in-distribution (ID) images. While prompt learning methods such as CoOp have shown effectiveness and efficiency in few-shot ID classification, they still face limitations in OOD detection due to the potential presence of ID-irrelevant information in text embeddings. To address this issue, we introduce a new approach called \textbf{Lo}cal regularized \textbf{Co}ntext \textbf{Op}timization (LoCoOp), which performs OOD regularization that utilizes the portions of CLIP local features as OOD features during training. CLIP's local features have a lot of ID-irrelevant nuisances (e.g., backgrounds), and by learning to push them away from the ID class text embeddings, we can remove the nuisances in the ID class text embeddings and enhance the separation between ID and OOD. Experiments on the large-scale ImageNet OOD detection benchmarks demonstrate the superiority of our LoCoOp over zero-shot, fully supervised detection methods and prompt learning methods. Notably, even in a one-shot setting -- just one label per class, LoCoOp outperforms existing zero-shot and fully supervised detection methods. The code will be available via \url{https://github.com/AtsuMiyai/LoCoOp}.

Authors:Hamed Damirchi, Forest Agostinelli, Pooyan Jamshidi

Abstract: Monolithic neural networks that make use of a single set of weights to learn useful representations for downstream tasks explicitly dismiss the compositional nature of data generation processes. This characteristic exists in data where every instance can be regarded as the combination of an identity concept, such as the shape of an object, combined with modifying concepts, such as orientation, color, and size. The dismissal of compositionality is especially detrimental in robotics, where state estimation relies heavily on the compositional nature of physical mechanisms (e.g., rotations and transformations) to model interactions. To accommodate this data characteristic, modular networks have been proposed. However, a lack of structure in each module's role, and modular network-specific issues such as module collapse have restricted their usability. We propose a modular network architecture that accommodates the mentioned decompositional concept by proposing a unique structure that splits the modules into predetermined roles. Additionally, we provide regularizations that improve the resiliency of the modular network to the problem of module collapse while improving the decomposition accuracy of the model.

Authors:Zehui Liao, Yutong Xie, Shishuai Hu, Yong Xia

Abstract: Manual medical image segmentation is subjective and suffers from annotator-related bias, which can be mimicked or amplified by deep learning methods. Recently, researchers have suggested that such bias is the combination of the annotator preference and stochastic error, which are modeled by convolution blocks located after decoder and pixel-wise independent Gaussian distribution, respectively. It is unlikely that convolution blocks can effectively model the varying degrees of preference at the full resolution level. Additionally, the independent pixel-wise Gaussian distribution disregards pixel correlations, leading to a discontinuous boundary. This paper proposes a Transformer-based Annotation Bias-aware (TAB) medical image segmentation model, which tackles the annotator-related bias via modeling annotator preference and stochastic errors. TAB employs the Transformer with learnable queries to extract the different preference-focused features. This enables TAB to produce segmentation with various preferences simultaneously using a single segmentation head. Moreover, TAB takes the multivariant normal distribution assumption that models pixel correlations, and learns the annotation distribution to disentangle the stochastic error. We evaluated our TAB on an OD/OC segmentation benchmark annotated by six annotators. Our results suggest that TAB outperforms existing medical image segmentation models which take into account the annotator-related bias.

Authors:Long Ma, Dian Jin, Nan An, Jinyuan Liu, Xin Fan, Risheng Liu

Abstract: Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. The mainstream learning-based methods mainly acquire the enhanced model by learning the data distribution from the specific scenes, causing poor adaptability (even failure) when meeting real-world scenarios that have never been encountered before. The main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes. To remedy this, we first explore relationships between diverse low-light scenes based on statistical analysis, i.e., the network parameters of the encoder trained in different data distributions are close. We introduce the bilevel paradigm to model the above latent correspondence from the perspective of hyperparameter optimization. A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes (i.e., freezing the encoder in the adaptation and testing phases). Further, we define a reinforced bilevel learning framework to provide a meta-initialization for scene-specific decoder to further ameliorate visual quality. Moreover, to improve the practicability, we establish a Retinex-induced architecture with adaptive denoising and apply our built learning framework to acquire its parameters by using two training losses including supervised and unsupervised forms. Extensive experimental evaluations on multiple datasets verify our adaptability and competitive performance against existing state-of-the-art works. The code and datasets will be available at https://github.com/vis-opt-group/BL.

Authors:Josef Bengtson, David Nilsson, Che-Tsung Lin, Marcel Büsching, Fredrik Kahl

Abstract: We present a generalizable novel view synthesis method where it is possible to modify the visual appearance of rendered views to match a target weather or lighting condition. Our method is based on a generalizable transformer architecture, trained on synthetically generated scenes under different appearance conditions. This allows for rendering novel views in a consistent manner of 3D scenes that were not included in the training set, along with the ability to (i) modify their appearance to match the target condition and (ii) smoothly interpolate between different conditions. Experiments on both real and synthetic scenes are provided including both qualitative and quantitative evaluations. Please refer to our project page for video results: https://ava-nvs.github.io/

Authors:Tejasvee Bisen, Mohammed Javed, Shashank Kirtania, P. Nagabhushan

Abstract: For any digital application with document images such as retrieval, the classification of document images becomes an essential stage. Conventionally for the purpose, the full versions of the documents, that is the uncompressed document images make the input dataset, which poses a threat due to the big volume required to accommodate the full versions of the documents. Therefore, it would be novel, if the same classification task could be accomplished directly (with some partial decompression) with the compressed representation of documents in order to make the whole process computationally more efficient. In this research work, a novel deep learning model, DWT CompCNN is proposed for classification of documents that are compressed using High Throughput JPEG 2000 (HTJ2K) algorithm. The proposed DWT-CompCNN comprises of five convolutional layers with filter sizes of 16, 32, 64, 128, and 256 consecutively for each increasing layer to improve learning from the wavelet coefficients extracted from the compressed images. Experiments are performed on two benchmark datasets- Tobacco-3482 and RVL-CDIP, which demonstrate that the proposed model is time and space efficient, and also achieves a better classification accuracy in compressed domain.

Authors:Mischa Dombrowski, Bernhard Kainz

Abstract: Recent advances in score-based generative models have led to a huge spike in the development of downstream applications using generative models ranging from data augmentation over image and video generation to anomaly detection. Despite publicly available trained models, their potential to be used for privacy preserving data sharing has not been fully explored yet. Training diffusion models on private data and disseminating the models and weights rather than the raw dataset paves the way for innovative large-scale data-sharing strategies, particularly in healthcare, where safeguarding patients' personal health information is paramount. However, publishing such models without individual consent of, e.g., the patients from whom the data was acquired, necessitates guarantees that identifiable training samples will never be reproduced, thus protecting personal health data and satisfying the requirements of policymakers and regulatory bodies. This paper introduces a method for estimating the upper bound of the probability of reproducing identifiable training images during the sampling process. This is achieved by designing an adversarial approach that searches for anatomic fingerprints, such as medical devices or dermal art, which could potentially be employed to re-identify training images. Our method harnesses the learned score-based model to estimate the probability of the entire subspace of the score function that may be utilized for one-to-one reproduction of training samples. To validate our estimates, we generate anomalies containing a fingerprint and investigate whether generated samples from trained generative models can be uniquely mapped to the original training samples. Overall our results show that privacy-breaching images are reproduced at sampling time if the models were trained without care.

Authors:Minho Shim, Taeoh Kim, Jinhyung Kim, Dongyoon Wee

Abstract: Summarizing a video requires a diverse understanding of the video, ranging from recognizing scenes to evaluating how much each frame is essential enough to be selected as a summary. Self-supervised learning (SSL) is acknowledged for its robustness and flexibility to multiple downstream tasks, but the video SSL has not shown its value for dense understanding tasks like video summarization. We claim an unsupervised autoencoder with sufficient self-supervised learning does not need any extra downstream architecture design or fine-tuning weights to be utilized as a video summarization model. The proposed method to evaluate the importance score of each frame takes advantage of the reconstruction score of the autoencoder's decoder. We evaluate the method in major unsupervised video summarization benchmarks to show its effectiveness under various experimental settings.

Authors:Xavier F. Cadet, Ranya Aloufi, Alain Miranville, Sara Ahmadi-Abhari, Hamed Haddadi

Abstract: Despite impressive empirical advances of SSL in solving various tasks, the problem of understanding and characterizing SSL representations learned from input data remains relatively under-explored. We provide a comparative analysis of how the representations produced by SSL models differ when masking parts of the input. Specifically, we considered state-of-the-art SSL pretrained models, such as DINOv2, MAE, and SwaV, and analyzed changes at the representation levels across 4 Image Classification datasets. First, we generate variations of the datasets by applying foreground and background segmentation. Then, we conduct statistical analysis using Canonical Correlation Analysis (CCA) and Centered Kernel Alignment (CKA) to evaluate the robustness of the representations learned in SSL models. Empirically, we show that not all models lead to representations that separate foreground, background, and complete images. Furthermore, we test different masking strategies by occluding the center regions of the images to address cases where foreground and background are difficult. For example, the DTD dataset that focuses on texture rather specific objects.

Authors:Baorui Ma, Yu-Shen Liu, Zhizhong Han

Abstract: Learning signed distance functions (SDFs) from 3D point clouds is an important task in 3D computer vision. However, without ground truth signed distances, point normals or clean point clouds, current methods still struggle from learning SDFs from noisy point clouds. To overcome this challenge, we propose to learn SDFs via a noise to noise mapping, which does not require any clean point cloud or ground truth supervision for training. Our novelty lies in the noise to noise mapping which can infer a highly accurate SDF of a single object or scene from its multiple or even single noisy point cloud observations. Our novel learning manner is supported by modern Lidar systems which capture multiple noisy observations per second. We achieve this by a novel loss which enables statistical reasoning on point clouds and maintains geometric consistency although point clouds are irregular, unordered and have no point correspondence among noisy observations. Our evaluation under the widely used benchmarks demonstrates our superiority over the state-of-the-art methods in surface reconstruction, point cloud denoising and upsampling. Our code, data, and pre-trained models are available at https://github.com/mabaorui/Noise2NoiseMapping/

Authors:Federico Nocentini, Claudio Ferrari, Stefano Berretti

Abstract: This paper presents a novel approach for generating 3D talking heads from raw audio inputs. Our method grounds on the idea that speech related movements can be comprehensively and efficiently described by the motion of a few control points located on the movable parts of the face, i.e., landmarks. The underlying musculoskeletal structure then allows us to learn how their motion influences the geometrical deformations of the whole face. The proposed method employs two distinct models to this aim: the first one learns to generate the motion of a sparse set of landmarks from the given audio. The second model expands such landmarks motion to a dense motion field, which is utilized to animate a given 3D mesh in neutral state. Additionally, we introduce a novel loss function, named Cosine Loss, which minimizes the angle between the generated motion vectors and the ground truth ones. Using landmarks in 3D talking head generation offers various advantages such as consistency, reliability, and obviating the need for manual-annotation. Our approach is designed to be identity-agnostic, enabling high-quality facial animations for any users without additional data or training.

Authors:Roi Peleg, Roi Weiss, Assaf Hoogi

Abstract: Network optimization is a crucial step in the field of deep learning, as it directly affects the performance of models in various domains such as computer vision. Despite the numerous optimizers that have been developed over the years, the current methods are still limited in their ability to accurately and quickly identify gradient trends, which can lead to sub-optimal network performance. In this paper, we propose a novel deep optimizer called Fast-Adaptive Moment Estimation (FAME), which for the first time estimates gradient moments using a Triple Exponential Moving Average (TEMA). Incorporating TEMA into the optimization process provides richer and more accurate information on data changes and trends, as compared to the standard Exponential Moving Average used in essentially all current leading adaptive optimization methods. Our proposed FAME optimizer has been extensively validated through a wide range of benchmarks, including CIFAR-10, CIFAR-100, PASCAL-VOC, MS-COCO, and Cityscapes, using 14 different learning architectures, six optimizers, and various vision tasks, including detection, classification and semantic understanding. The results demonstrate that our FAME optimizer outperforms other leading optimizers in terms of both robustness and accuracy.

Authors:Yingjie Wang, Jiajun Deng, Yao Li, Jinshui Hu, Cong Liu, Yu Zhang, Jianmin Ji, Wanli Ouyang, Yanyong Zhang

Abstract: LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocity hints. Though seemingly natural, how to efficiently combine them for improved feature representation is still unclear. The main challenge arises from that Radar data are extremely sparse and lack height information. Therefore, directly integrating Radar features into LiDAR-centric detection networks is not optimal. In this work, we introduce a bi-directional LiDAR-Radar fusion framework, termed Bi-LRFusion, to tackle the challenges and improve 3D detection for dynamic objects. Technically, Bi-LRFusion involves two steps: first, it enriches Radar's local features by learning important details from the LiDAR branch to alleviate the problems caused by the absence of height information and extreme sparsity; second, it combines LiDAR features with the enhanced Radar features in a unified bird's-eye-view representation. We conduct extensive experiments on nuScenes and ORR datasets, and show that our Bi-LRFusion achieves state-of-the-art performance for detecting dynamic objects. Notably, Radar data in these two datasets have different formats, which demonstrates the generalizability of our method. Codes are available at https://github.com/JessieW0806/BiLRFusion.

Authors:Chia-Chun Chung, Pei-Chun Chang, Yong-Sheng Chen, HaoYuan He, Chinson Yeh

Abstract: Nowadays, deploying a robust face recognition product becomes easy with the development of face recognition techniques for decades. Not only profile image verification but also the state-of-the-art method can handle the in-the-wild image almost perfectly. However, the concern of privacy issues raise rapidly since mainstream research results are powered by tons of web-crawled data, which faces the privacy invasion issue. The community tries to escape this predicament completely by training the face recognition model with synthetic data but faces severe domain gap issues, which still need to access real images and identity labels to fine-tune the model. In this paper, we propose SASMU, a simple, novel, and effective method for face recognition using a synthetic dataset. Our proposed method consists of spatial data augmentation (SA) and spectrum mixup (SMU). We first analyze the existing synthetic datasets for developing a face recognition system. Then, we reveal that heavy data augmentation is helpful for boosting performance when using synthetic data. By analyzing the previous frequency mixup studies, we proposed a novel method for domain generalization. Extensive experimental results have demonstrated the effectiveness of SASMU, achieving state-of-the-art performance on several common benchmarks, such as LFW, AgeDB-30, CA-LFW, CFP-FP, and CP-LFW.

Authors:Jiawei Wu, Changqing Zhang, Zuoyong Li, Huazhu Fu, Xi Peng, Joey Tianyi Zhou

Abstract: Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing. Due to the highly ill-posed issue, additional inputs, typically user-defined trimaps or scribbles, are usually needed to reduce the uncertainty. Although effective, it is either time consuming or only suitable for experienced users who know where to place the strokes. In this work, we propose a decomposed-uncertainty-guided matting (dugMatting) algorithm, which explores the explicitly decomposed uncertainties to efficiently and effectively improve the results. Basing on the characteristic of these uncertainties, the epistemic uncertainty is reduced in the process of guiding interaction (which introduces prior knowledge), while the aleatoric uncertainty is reduced in modeling data distribution (which introduces statistics for both data and possible noise). The proposed matting framework relieves the requirement for users to determine the interaction areas by using simple and efficient labeling. Extensively quantitative and qualitative results validate that the proposed method significantly improves the original matting algorithms in terms of both efficiency and efficacy.

Authors:Jiacheng Chen, Ruizhi Deng, Yasutaka Furukawa

Abstract: This paper presents PolyDiffuse, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM), an emerging machinery amid exploding generative AI, while formulating reconstruction as a generation process conditioned on sensor data. The task of structured reconstruction poses two fundamental challenges to DM: 1) A structured geometry is a ``set'' (e.g., a set of polygons for a floorplan geometry), where a sample of $N$ elements has $N!$ different but equivalent representations, making the denoising highly ambiguous; and 2) A ``reconstruction'' task has a single solution, where an initial noise needs to be chosen carefully, while any initial noise works for a generation task. Our technical contribution is the introduction of a Guided Set Diffusion Model where 1) the forward diffusion process learns guidance networks to control noise injection so that one representation of a sample remains distinct from its other permutation variants, thus resolving denoising ambiguity; and 2) the reverse denoising process reconstructs polygonal shapes, initialized and directed by the guidance networks, as a conditional generation process subject to the sensor data. We have evaluated our approach for reconstructing two types of polygonal shapes: floorplan as a set of polygons and HD map for autonomous cars as a set of polylines. Through extensive experiments on standard benchmarks, we demonstrate that PolyDiffuse significantly advances the current state of the art and enables broader practical applications.

Authors:Xiaoyong Mei, Yi Yang, Ming Li, Changqin Huang, Kai Zhang, Pietro Lió

Abstract: Reference-based super-resolution (RefSR) has gained considerable success in the field of super-resolution with the addition of high-resolution reference images to reconstruct low-resolution (LR) inputs with more high-frequency details, thereby overcoming some limitations of single image super-resolution (SISR). Previous research in the field of RefSR has mostly focused on two crucial aspects. The first is accurate correspondence matching between the LR and the reference (Ref) image. The second is the effective transfer and aggregation of similar texture information from the Ref images. Nonetheless, an important detail of perceptual loss and adversarial loss has been underestimated, which has a certain adverse effect on texture transfer and reconstruction. In this study, we propose a feature reuse framework that guides the step-by-step texture reconstruction process through different stages, reducing the negative impacts of perceptual and adversarial loss. The feature reuse framework can be used for any RefSR model, and several RefSR approaches have improved their performance after being retrained using our framework. Additionally, we introduce a single image feature embedding module and a texture-adaptive aggregation module. The single image feature embedding module assists in reconstructing the features of the LR inputs itself and effectively lowers the possibility of including irrelevant textures. The texture-adaptive aggregation module dynamically perceives and aggregates texture information between the LR inputs and the Ref images using dynamic filters. This enhances the utilization of the reference texture while reducing reference misuse. The source code is available at https://github.com/Yi-Yang355/FRFSR.

Authors:David Hoffmann, Kai Norman Clasen, Begüm Demir

Abstract: In this paper, we introduce a novel Synchronized Class Token Fusion (SCT Fusion) architecture in the framework of multi-modal multi-label classification (MLC) of remote sensing (RS) images. The proposed architecture leverages modality-specific attention-based transformer encoders to process varying input modalities, while exchanging information across modalities by synchronizing the special class tokens after each transformer encoder block. The synchronization involves fusing the class tokens with a trainable fusion transformation, resulting in a synchronized class token that contains information from all modalities. As the fusion transformation is trainable, it allows to reach an accurate representation of the shared features among different modalities. Experimental results show the effectiveness of the proposed architecture over single-modality architectures and an early fusion multi-modal architecture when evaluated on a multi-modal MLC dataset. The code of the proposed architecture is publicly available at https://git.tu-berlin.de/rsim/sct-fusion.

Authors:Yun Chu, Pu Li, Yong Bai, Zhuhua Hu, Yongqing Chen, Jiafeng Lu

Abstract: Due to the over-parameterization of neural networks, many model compression methods based on pruning and quantization have emerged. They are remarkable in reducing the size, parameter number, and computational complexity of the model. However, most of the models compressed by such methods need the support of special hardware and software, which increases the deployment cost. Moreover, these methods are mainly used in classification tasks, and rarely directly used in detection tasks. To address these issues, for the object detection network we introduce a three-stage model compression method: dynamic sparse training, group channel pruning, and spatial attention distilling. Firstly, to select out the unimportant channels in the network and maintain a good balance between sparsity and accuracy, we put forward a dynamic sparse training method, which introduces a variable sparse rate, and the sparse rate will change with the training process of the network. Secondly, to reduce the effect of pruning on network accuracy, we propose a novel pruning method called group channel pruning. In particular, we divide the network into multiple groups according to the scales of the feature layer and the similarity of module structure in the network, and then we use different pruning thresholds to prune the channels in each group. Finally, to recover the accuracy of the pruned network, we use an improved knowledge distillation method for the pruned network. Especially, we extract spatial attention information from the feature maps of specific scales in each group as knowledge for distillation. In the experiments, we use YOLOv4 as the object detection network and PASCAL VOC as the training dataset. Our method reduces the parameters of the model by 64.7 % and the calculation by 34.9%.

Authors:Zheng Chen, Yan-Pei Cao, Yuan-Chen Guo, Chen Wang, Ying Shan, Song-Hai Zhang

Abstract: Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly used in these applications to reduce network bandwidth and storage requirements. However, synthesizing novel views from these panoramas remains a key challenge. Although existing neural radiance field methods can produce photorealistic views under narrow-baseline and dense image captures, they tend to overfit the training views when dealing with \emph{wide-baseline} panoramas due to the difficulty in learning accurate geometry from sparse $360^{\circ}$ views. To address this problem, we propose PanoGRF, Generalizable Spherical Radiance Fields for Wide-baseline Panoramas, which construct spherical radiance fields incorporating $360^{\circ}$ scene priors. Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection. Moreover, as some regions of the panorama are only visible from one view while invisible from others under wide baseline settings, PanoGRF incorporates $360^{\circ}$ monocular depth priors into spherical depth estimation to improve the geometry features. Experimental results on multiple panoramic datasets demonstrate that PanoGRF significantly outperforms state-of-the-art generalizable view synthesis methods for wide-baseline panoramas (e.g., OmniSyn) and perspective images (e.g., IBRNet, NeuRay).

Authors:Lei Ke, Mingqiao Ye, Martin Danelljan, Yifan Liu, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu

Abstract: The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction quality falls short in many cases, particularly when dealing with objects that have intricate structures. We propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability. Our careful design reuses and preserves the pre-trained model weights of SAM, while only introducing minimal additional parameters and computation. We design a learnable High-Quality Output Token, which is injected into SAM's mask decoder and is responsible for predicting the high-quality mask. Instead of only applying it on mask-decoder features, we first fuse them with early and final ViT features for improved mask details. To train our introduced learnable parameters, we compose a dataset of 44K fine-grained masks from several sources. HQ-SAM is only trained on the introduced detaset of 44k masks, which takes only 4 hours on 8 GPUs. We show the efficacy of HQ-SAM in a suite of 9 diverse segmentation datasets across different downstream tasks, where 7 out of them are evaluated in a zero-shot transfer protocol. Our code and models will be released at https://github.com/SysCV/SAM-HQ.

Authors:Arun K. Sharma, Nishchal K. Sharma

Abstract: Biomedical image classification requires capturing of bio-informatics based on specific feature distribution. In most of such applications, there are mainly challenges due to limited availability of samples for diseased cases and imbalanced nature of dataset. This article presents the novel framework of multi-head self-attention for vision transformer (ViT) which makes capable of capturing the specific image features for classification and analysis. The proposed method uses the concept of residual connection for accumulating the best attention output in each block of multi-head attention. The proposed framework has been evaluated on two small datasets: (i) blood cell classification dataset and (ii) brain tumor detection using brain MRI images. The results show the significant improvement over traditional ViT and other convolution based state-of-the-art classification models.

Authors:Axel Barroso-Laguna, Eric Brachmann, Victor Adrian Prisacariu, Gabriel J. Brostow, Daniyar Turmukhambetov

Abstract: Camera pose estimation for two-view geometry traditionally relies on RANSAC. Normally, a multitude of image correspondences leads to a pool of proposed hypotheses, which are then scored to find a winning model. The inlier count is generally regarded as a reliable indicator of "consensus". We examine this scoring heuristic, and find that it favors disappointing models under certain circumstances. As a remedy, we propose the Fundamental Scoring Network (FSNet), which infers a score for a pair of overlapping images and any proposed fundamental matrix. It does not rely on sparse correspondences, but rather embodies a two-view geometry model through an epipolar attention mechanism that predicts the pose error of the two images. FSNet can be incorporated into traditional RANSAC loops. We evaluate FSNet on fundamental and essential matrix estimation on indoor and outdoor datasets, and establish that FSNet can successfully identify good poses for pairs of images with few or unreliable correspondences. Besides, we show that naively combining FSNet with MAGSAC++ scoring approach achieves state of the art results.

Authors:Yihong Cao, Hui Zhang, Xiao Lu, Zheng Xiao, Kailun Yang, Yaonan Wang

Abstract: Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. Code will be made publicly available at https://github.com/yihong-97/Source-free_IAPC.

Authors:Anirudh Sriram, Adrien Gaidon, Jiajun Wu, Juan Carlos Niebles, Li Fei-Fei, Ehsan Adeli

Abstract: Recent advances in self-supervised representation learning have enabled more efficient and robust model performance without relying on extensive labeled data. However, most works are still focused on images, with few working on videos and even fewer on multi-view videos, where more powerful inductive biases can be leveraged for self-supervision. In this work, we propose a novel method for representation learning of multi-view videos, where we explicitly model the representation space to maintain Homography Equivariance (HomE). Our method learns an implicit mapping between different views, culminating in a representation space that maintains the homography relationship between neighboring views. We evaluate our HomE representation via action recognition and pedestrian intent prediction as downstream tasks. On action classification, our method obtains 96.4% 3-fold accuracy on the UCF101 dataset, better than most state-of-the-art self-supervised learning methods. Similarly, on the STIP dataset, we outperform the state-of-the-art by 6% for pedestrian intent prediction one second into the future while also obtaining an accuracy of 91.2% for pedestrian action (cross vs. not-cross) classification. Code is available at https://github.com/anirudhs123/HomE.

Authors:Aleixo Cambeiro Barreiro, Mariusz Trzeciakiewicz, Anna Hilsmann, Peter Eisert

Abstract: Digitalization of existing buildings and the creation of 3D BIM models for them has become crucial for many tasks. Of particular importance are floor plans, which contain information about building layouts and are vital for processes such as construction, maintenance or refurbishing. However, this data is not always available in digital form, especially for older buildings constructed before CAD tools were widely available, or lacks semantic information. The digitalization of such information usually requires manual work of an expert that must reconstruct the layouts by hand, which is a cumbersome and error-prone process. In this paper, we present a pipeline for reconstruction of vectorized 3D models from scanned 2D plans, aiming at increasing the efficiency of this process. The method presented achieves state-of-the-art results in the public dataset CubiCasa5k, and shows good generalization to different types of plans. Our vectorization approach is particularly effective, outperforming previous methods.

Authors:Ahmed Amer, Chirag Bhuvaneshwara, Gowtham K. Addluri, Mohammed M. Shaik, Vedant Bonde, Philipp Müller

Abstract: Listeners use short interjections, so-called backchannels, to signify attention or express agreement. The automatic analysis of this behavior is of key importance for human conversation analysis and interactive conversational agents. Current state-of-the-art approaches for backchannel analysis from visual behavior make use of two types of features: features based on body pose and features based on facial behavior. At the same time, transformer neural networks have been established as an effective means to fuse input from different data sources, but they have not yet been applied to backchannel analysis. In this work, we conduct a comprehensive evaluation of multi-modal transformer architectures for automatic backchannel analysis based on pose and facial information. We address both the detection of backchannels as well as the task of estimating the agreement expressed in a backchannel. In evaluations on the MultiMediate'22 backchannel detection challenge, we reach 66.4% accuracy with a one-layer transformer architecture, outperforming the previous state of the art. With a two-layer transformer architecture, we furthermore set a new state of the art (0.0604 MSE) on the task of estimating the amount of agreement expressed in a backchannel.

Authors:Ivana Balažević, David Steiner, Nikhil Parthasarathy, Relja Arandjelović, Olivier J. Hénaff

Abstract: In-context learning$\unicode{x2013}$the ability to configure a model's behavior with different prompts$\unicode{x2013}$has revolutionized the field of natural language processing, alleviating the need for task-specific models and paving the way for generalist models capable of assisting with any query. Computer vision, in contrast, has largely stayed in the former regime: specialized decoders and finetuning protocols are generally required to perform dense tasks such as semantic segmentation and depth estimation. In this work we explore a simple mechanism for in-context learning of such scene understanding tasks: nearest neighbor retrieval from a prompt of annotated features. We propose a new pretraining protocol$\unicode{x2013}$leveraging attention within and across images$\unicode{x2013}$which yields representations particularly useful in this regime. The resulting Hummingbird model, suitably prompted, performs various scene understanding tasks without modification while approaching the performance of specialists that have been finetuned for each task. Moreover, Hummingbird can be configured to perform new tasks much more efficiently than finetuned models, raising the possibility of scene understanding in the interactive assistant regime.

Authors:Cristina Menghini, Andrew Delworth, Stephen H. Bach

Abstract: Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e., heuristic labels for unlabeled data, to enhance CLIP via prompt tuning. Conventional pseudolabeling trains a model on labeled data and then generates labels for unlabeled data. VLMs' zero-shot capabilities enable a ``second generation'' of pseudolabeling approaches that do not require task-specific training on labeled data. By using zero-shot pseudolabels as a source of supervision, we observe that learning paradigms such as semi-supervised, transductive zero-shot, and unsupervised learning can all be seen as optimizing the same loss function. This unified view enables the development of versatile training strategies that are applicable across learning paradigms. We investigate them on image classification tasks where CLIP exhibits limitations, by varying prompt modalities, e.g., textual or visual prompts, and learning paradigms. We find that (1) unexplored prompt tuning strategies that iteratively refine pseudolabels consistently improve CLIP accuracy, by 19.5 points in semi-supervised learning, by 28.4 points in transductive zero-shot learning, and by 15.2 points in unsupervised learning, and (2) unlike conventional semi-supervised pseudolabeling, which exacerbates model biases toward classes with higher-quality pseudolabels, prompt tuning leads to a more equitable distribution of per-class accuracy. The code to reproduce the experiments is at github.com/BatsResearch/menghini-enhanceCLIPwithCLIP-code.

Authors:Jinman Park, Francois Barnard, Saad Hossain, Sirisha Rambhatla, Paul Fieguth

Abstract: Unsupervised domain adaptation (UDA) aims to bridge the gap between source and target domains in the absence of target domain labels using two main techniques: input-level alignment (such as generative modeling and stylization) and feature-level alignment (which matches the distribution of the feature maps, e.g. gradient reversal layers). Motivated from the success of generative modeling for image classification, stylization-based methods were recently proposed for regression tasks, such as pose estimation. However, use of input-level alignment via generative modeling and stylization incur additional overhead and computational complexity which limit their use in real-world DA tasks. To investigate the role of input-level alignment for DA, we ask the following question: Is generative modeling-based stylization necessary for visual domain adaptation in regression? Surprisingly, we find that input-alignment has little effect on regression tasks as compared to classification. Based on these insights, we develop a non-parametric feature-level domain alignment method -- Implicit Stylization (ImSty) -- which results in consistent improvements over SOTA regression task, without the need for computationally intensive stylization and generative modeling. Our work conducts a critical evaluation of the role of generative modeling and stylization, at a time when these are also gaining popularity for domain generalization.

Authors:Zeqiang Lai, Yuchen Duan, Jifeng Dai, Ziheng Li, Ying Fu, Hongsheng Li, Yu Qiao, Wenhai Wang

Abstract: The evolution of semantic segmentation has long been dominated by learning more discriminative image representations for classifying each pixel. Despite the prominent advancements, the priors of segmentation masks themselves, e.g., geometric and semantic constraints, are still under-explored. In this paper, we propose to ameliorate the semantic segmentation quality of existing discriminative approaches with a mask prior modeled by a recently-developed denoising diffusion generative model. Beginning with a unified architecture that adapts diffusion models for mask prior modeling, we focus this work on a specific instantiation with discrete diffusion and identify a variety of key design choices for its successful application. Our exploratory analysis revealed several important findings, including: (1) a simple integration of diffusion models into semantic segmentation is not sufficient, and a poorly-designed diffusion process might lead to degradation in segmentation performance; (2) during the training, the object to which noise is added is more important than the type of noise; (3) during the inference, the strict diffusion denoising scheme may not be essential and can be relaxed to a simpler scheme that even works better. We evaluate the proposed prior modeling with several off-the-shelf segmentors, and our experimental results on ADE20K and Cityscapes demonstrate that our approach could achieve competitively quantitative performance and more appealing visual quality.

Authors:Hanyuan Liu, Minshan Xie, Jinbo Xing, Chengze Li, Tien-Tsin Wong

Abstract: Video colorization is a challenging task that involves inferring plausible and temporally consistent colors for grayscale frames. In this paper, we present ColorDiffuser, an adaptation of a pre-trained text-to-image latent diffusion model for video colorization. With the proposed adapter-based approach, we repropose the pre-trained text-to-image model to accept input grayscale video frames, with the optional text description, for video colorization. To enhance the temporal coherence and maintain the vividness of colorization across frames, we propose two novel techniques: the Color Propagation Attention and Alternated Sampling Strategy. Color Propagation Attention enables the model to refine its colorization decision based on a reference latent frame, while Alternated Sampling Strategy captures spatiotemporal dependencies by using the next and previous adjacent latent frames alternatively as reference during the generative diffusion sampling steps. This encourages bidirectional color information propagation between adjacent video frames, leading to improved color consistency across frames. We conduct extensive experiments on benchmark datasets, and the results demonstrate the effectiveness of our proposed framework. The evaluations show that ColorDiffuser achieves state-of-the-art performance in video colorization, surpassing existing methods in terms of color fidelity, temporal consistency, and visual quality.

Authors:Srikar Appalaraju, Peng Tang, Qi Dong, Nishant Sankaran, Yichu Zhou, R. Manmatha

Abstract: We propose DocFormerv2, a multi-modal transformer for Visual Document Understanding (VDU). The VDU domain entails understanding documents (beyond mere OCR predictions) e.g., extracting information from a form, VQA for documents and other tasks. VDU is challenging as it needs a model to make sense of multiple modalities (visual, language and spatial) to make a prediction. Our approach, termed DocFormerv2 is an encoder-decoder transformer which takes as input - vision, language and spatial features. DocFormerv2 is pre-trained with unsupervised tasks employed asymmetrically i.e., two novel document tasks on encoder and one on the auto-regressive decoder. The unsupervised tasks have been carefully designed to ensure that the pre-training encourages local-feature alignment between multiple modalities. DocFormerv2 when evaluated on nine datasets shows state-of-the-art performance over strong baselines e.g. TabFact (4.3%), InfoVQA (1.4%), FUNSD (1%). Furthermore, to show generalization capabilities, on three VQA tasks involving scene-text, Doc- Formerv2 outperforms previous comparably-sized models and even does better than much larger models (such as GIT2, PaLi and Flamingo) on some tasks. Extensive ablations show that due to its pre-training, DocFormerv2 understands multiple modalities better than prior-art in VDU.

Authors:Xiuye Gu, Yin Cui, Jonathan Huang, Abdullah Rashwan, Xuan Yang, Xingyi Zhou, Golnaz Ghiasi, Weicheng Kuo, Huizhong Chen, Liang-Chieh Chen, David A Ross

Abstract: Observing the close relationship among panoptic, semantic and instance segmentation tasks, we propose to train a universal multi-dataset multi-task segmentation model: DaTaSeg.We use a shared representation (mask proposals with class predictions) for all tasks. To tackle task discrepancy, we adopt different merge operations and post-processing for different tasks. We also leverage weak-supervision, allowing our segmentation model to benefit from cheaper bounding box annotations. To share knowledge across datasets, we use text embeddings from the same semantic embedding space as classifiers and share all network parameters among datasets. We train DaTaSeg on ADE semantic, COCO panoptic, and Objects365 detection datasets. DaTaSeg improves performance on all datasets, especially small-scale datasets, achieving 54.0 mIoU on ADE semantic and 53.5 PQ on COCO panoptic. DaTaSeg also enables weakly-supervised knowledge transfer on ADE panoptic and Objects365 instance segmentation. Experiments show DaTaSeg scales with the number of training datasets and enables open-vocabulary segmentation through direct transfer. In addition, we annotate an Objects365 instance segmentation set of 1,000 images and will release it as a public benchmark.

Authors:Zhangyang Qi, Jiaqi Wang, Xiaoyang Wu, Hengshuang Zhao

Abstract: Multi-view 3D object detection is becoming popular in autonomous driving due to its high effectiveness and low cost. Most of the current state-of-the-art detectors follow the query-based bird's-eye-view (BEV) paradigm, which benefits from both BEV's strong perception power and end-to-end pipeline. Despite achieving substantial progress, existing works model objects via globally leveraging temporal and spatial information of BEV features, resulting in problems when handling the challenging complex and dynamic autonomous driving scenarios. In this paper, we proposed an Object-Centric query-BEV detector OCBEV, which can carve the temporal and spatial cues of moving targets more effectively. OCBEV comprises three designs: Object Aligned Temporal Fusion aligns the BEV feature based on ego-motion and estimated current locations of moving objects, leading to a precise instance-level feature fusion. Object Focused Multi-View Sampling samples more 3D features from an adaptive local height ranges of objects for each scene to enrich foreground information. Object Informed Query Enhancement replaces part of pre-defined decoder queries in common DETR-style decoders with positional features of objects on high-confidence locations, introducing more direct object positional priors. Extensive experimental evaluations are conducted on the challenging nuScenes dataset. Our approach achieves a state-of-the-art result, surpassing the traditional BEVFormer by 1.5 NDS points. Moreover, we have a faster convergence speed and only need half of the training iterations to get comparable performance, which further demonstrates its effectiveness.

Authors:Jiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash, Z. Morley Mao, Chaowei Xiao

Abstract: Perception is crucial in the realm of autonomous driving systems, where bird's eye view (BEV)-based architectures have recently reached state-of-the-art performance. The desirability of self-supervised representation learning stems from the expensive and laborious process of annotating 2D and 3D data. Although previous research has investigated pretraining methods for both LiDAR and camera-based 3D object detection, a unified pretraining framework for multimodal BEV perception is missing. In this study, we introduce CALICO, a novel framework that applies contrastive objectives to both LiDAR and camera backbones. Specifically, CALICO incorporates two stages: point-region contrast (PRC) and region-aware distillation (RAD). PRC better balances the region- and scene-level representation learning on the LiDAR modality and offers significant performance improvement compared to existing methods. RAD effectively achieves contrastive distillation on our self-trained teacher model. CALICO's efficacy is substantiated by extensive evaluations on 3D object detection and BEV map segmentation tasks, where it delivers significant performance improvements. Notably, CALICO outperforms the baseline method by 10.5% and 8.6% on NDS and mAP. Moreover, CALICO boosts the robustness of multimodal 3D object detection against adversarial attacks and corruption. Additionally, our framework can be tailored to different backbones and heads, positioning it as a promising approach for multimodal BEV perception.

Authors:Hyojun Go, JinYoung Kim, Yunsung Lee, Seunghyun Lee, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi

Abstract: Diffusion-based generative models have achieved remarkable success in various domains. It trains a model on denoising tasks that encompass different noise levels simultaneously, representing a form of multi-task learning (MTL). However, analyzing and improving diffusion models from an MTL perspective remains under-explored. In particular, MTL can sometimes lead to the well-known phenomenon of $\textit{negative transfer}$, which results in the performance degradation of certain tasks due to conflicts between tasks. In this paper, we aim to analyze diffusion training from an MTL standpoint, presenting two key observations: $\textbf{(O1)}$ the task affinity between denoising tasks diminishes as the gap between noise levels widens, and $\textbf{(O2)}$ negative transfer can arise even in the context of diffusion training. Building upon these observations, our objective is to enhance diffusion training by mitigating negative transfer. To achieve this, we propose leveraging existing MTL methods, but the presence of a huge number of denoising tasks makes this computationally expensive to calculate the necessary per-task loss or gradient. To address this challenge, we propose clustering the denoising tasks into small task clusters and applying MTL methods to them. Specifically, based on $\textbf{(O2)}$, we employ interval clustering to enforce temporal proximity among denoising tasks within clusters. We show that interval clustering can be solved with dynamic programming and utilize signal-to-noise ratio, timestep, and task affinity for clustering objectives. Through this, our approach addresses the issue of negative transfer in diffusion models by allowing for efficient computation of MTL methods. We validate the proposed clustering and its integration with MTL methods through various experiments, demonstrating improved sample quality of diffusion models.

Authors:Jackson Kaunismaa, Michael Guerzhoy

Abstract: Convolutional Neural Networks (ConvNets) usually rely on edge/shape information to classify images. Visualization methods developed over the last decade confirm that ConvNets rely on edge information. We investigate situations where the ConvNet needs to rely on image intensity in addition to shape. We show that the ConvNet relies on image intensity information using visualization.

Authors:Yongtuo Liu, Sara Magliacane, Miltiadis Kofinas, Efstratios Gavves

Abstract: Dynamical systems with complex behaviours, e.g. immune system cells interacting with a pathogen, are commonly modelled by splitting the behaviour into different regimes, or modes, each with simpler dynamics, and then learning the switching behaviour from one mode to another. Switching Dynamical Systems (SDS) are a powerful tool that automatically discovers these modes and mode-switching behaviour from time series data. While effective, these methods focus on independent objects, where the modes of one object are independent of the modes of the other objects. In this paper, we focus on the more general interacting object setting for switching dynamical systems, where the per-object dynamics also depends on an unknown and dynamically changing subset of other objects and their modes. To this end, we propose a novel graph-based approach for switching dynamical systems, GRAph Switching dynamical Systems (GRASS), in which we use a dynamic graph to characterize interactions between objects and learn both intra-object and inter-object mode-switching behaviour. We introduce two new datasets for this setting, a synthesized ODE-driven particles dataset and a real-world Salsa Couple Dancing dataset. Experiments show that GRASS can consistently outperforms previous state-of-the-art methods.

Authors:Anant Khandelwal, Happy Mittal, Shreyas Sunil Kulkarni, Deepak Gupta

Abstract: E-commerce websites (e.g. Amazon) have a plethora of structured and unstructured information (text and images) present on the product pages. Sellers often either don't label or mislabel values of the attributes (e.g. color, size etc.) for their products. Automatically identifying these attribute values from an eCommerce product page that contains both text and images is a challenging task, especially when the attribute value is not explicitly mentioned in the catalog. In this paper, we present a scalable solution for this problem where we pose attribute extraction problem as a question-answering task, which we solve using \textbf{MXT}, consisting of three key components: (i) \textbf{M}AG (Multimodal Adaptation Gate), (ii) \textbf{X}ception network, and (iii) \textbf{T}5 encoder-decoder. Our system consists of a generative model that \emph{generates} attribute-values for a given product by using both textual and visual characteristics (e.g. images) of the product. We show that our system is capable of handling zero-shot attribute prediction (when attribute value is not seen in training data) and value-absent prediction (when attribute value is not mentioned in the text) which are missing in traditional classification-based and NER-based models respectively. We have trained our models using distant supervision, removing dependency on human labeling, thus making them practical for real-world applications. With this framework, we are able to train a single model for 1000s of (product-type, attribute) pairs, thus reducing the overhead of training and maintaining separate models. Extensive experiments on two real world datasets show that our framework improves the absolute [email protected] by 10.16\% and 6.9\% from the existing state of the art models. In a popular e-commerce store, we have deployed our models for 1000s of (product-type, attribute) pairs.

Authors:Martin Hermann Paul Fuchs, Begüm Demir

Abstract: The development of learning-based hyperspectral image compression methods has recently attracted great attention in remote sensing. Such methods require a high number of hyperspectral images to be used during training to optimize all parameters and reach a high compression performance. However, existing hyperspectral datasets are not sufficient to train and evaluate learning-based compression methods, which hinders the research in this field. To address this problem, in this paper we present HySpecNet-11k that is a large-scale hyperspectral benchmark dataset made up of 11,483 nonoverlapping image patches. Each patch is a portion of 128 $\times$ 128 pixels with 224 spectral bands and a ground sample distance of 30 m. We exploit HySpecNet-11k to benchmark the current state of the art in learning-based hyperspectral image compression by focussing our attention on various 1D, 2D and 3D convolutional autoencoder architectures. Nevertheless, HySpecNet-11k can be used for any unsupervised learning task in the framework of hyperspectral image analysis. The dataset, our code and the pre-trained weights are publicly available at https://hyspecnet.rsim.berlin.

Authors:Wuxuan Shi, Mang Ye, Bo Du

Abstract: Color-guided depth super-resolution (DSR) is an encouraging paradigm that enhances a low-resolution (LR) depth map guided by an extra high-resolution (HR) RGB image from the same scene. Existing methods usually use interpolation to upscale the depth maps before feeding them into the network and transfer the high-frequency information extracted from HR RGB images to guide the reconstruction of depth maps. However, the extracted high-frequency information usually contains textures that are not present in depth maps in the existence of the cross-modality gap, and the noises would be further aggravated by interpolation due to the resolution gap between the RGB and depth images. To tackle these challenges, we propose a novel Symmetric Uncertainty-aware Feature Transmission (SUFT) for color-guided DSR. (1) For the resolution gap, SUFT builds an iterative up-and-down sampling pipeline, which makes depth features and RGB features spatially consistent while suppressing noise amplification and blurring by replacing common interpolated pre-upsampling. (2) For the cross-modality gap, we propose a novel Symmetric Uncertainty scheme to remove parts of RGB information harmful to the recovery of HR depth maps. Extensive experiments on benchmark datasets and challenging real-world settings suggest that our method achieves superior performance compared to state-of-the-art methods. Our code and models are available at https://github.com/ShiWuxuan/SUFT.

Authors:Shengqin Jiang, Yaoyu Fang, Haokui Zhang, Peng Wang, Yuankai Qi, Qingshan Liu

Abstract: With the rise in popularity of video-based social media, new categories of videos are constantly being generated, creating an urgent need for robust incremental learning techniques for video understanding. One of the biggest challenges in this task is catastrophic forgetting, where the network tends to forget previously learned data while learning new categories. To overcome this issue, knowledge distillation is a widely used technique for rehearsal-based video incremental learning that involves transferring important information on similarities among different categories to enhance the student model. Therefore, it is preferable to have a strong teacher model to guide the students. However, the limited performance of the network itself and the occurrence of catastrophic forgetting can result in the teacher network making inaccurate predictions for some memory exemplars, ultimately limiting the student network's performance. Based on these observations, we propose a teacher agent capable of generating stable and accurate soft labels to replace the output of the teacher model. This method circumvents the problem of knowledge misleading caused by inaccurate predictions of the teacher model and avoids the computational overhead of loading the teacher model for knowledge distillation. Extensive experiments demonstrate the advantages of our method, yielding significant performance improvements while utilizing only half the resolution of video clips in the incremental phases as input compared to recent state-of-the-art methods. Moreover, our method surpasses the performance of joint training when employing four times the number of samples in episodic memory.

Authors:Qihang Fan, Huaibo Huang, Xiaoqiang Zhou, Ran He

Abstract: Recent advancements in vision backbones have significantly improved their performance by simultaneously modeling images' local and global contexts. However, the bidirectional interaction between these two contexts has not been well explored and exploited, which is important in the human visual system. This paper proposes a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information as well as the bidirectional interaction between them in context-aware ways. Specifically, FASA employs self-modulated convolutions to adaptively extract local representation while utilizing self-attention in down-sampled space to extract global representation. Subsequently, it conducts a bidirectional adaptation process between local and global representation to model their interaction. In addition, we introduce a fine-grained downsampling strategy to enhance the down-sampled self-attention mechanism for finer-grained global perception capability. Based on FASA, we develop a family of lightweight vision backbones, Fully Adaptive Transformer (FAT) family. Extensive experiments on multiple vision tasks demonstrate that FAT achieves impressive performance. Notably, FAT accomplishes a 77.6% accuracy on ImageNet-1K using only 4.5M parameters and 0.7G FLOPs, which surpasses the most advanced ConvNets and Transformers with similar model size and computational costs. Moreover, our model exhibits faster speed on modern GPU compared to other models. Code will be available at https://github.com/qhfan/FAT.

Authors:Zewei Xu, Yuhang Lu, Touradj Ebrahimi

Abstract: Despite the huge success of deep convolutional neural networks in face recognition (FR) tasks, current methods lack explainability for their predictions because of their "black-box" nature. In recent years, studies have been carried out to give an interpretation of the decision of a deep FR system. However, the affinity between the input facial image and the extracted deep features has not been explored. This paper contributes to the problem of explainable face recognition by first conceiving a face reconstruction-based explanation module, which reveals the correspondence between the deep feature and the facial regions. To further interpret the decision of an FR model, a novel visual saliency explanation algorithm has been proposed. It provides insightful explanation by producing visual saliency maps that represent similar and dissimilar regions between input faces. A detailed analysis has been presented for the generated visual explanation to show the effectiveness of the proposed method.

Authors:Chang Liu, Shunxin Xu, Jialun Peng, Kaidong Zhang, Dong Liu

Abstract: One tough problem of image inpainting is to restore complex structures in the corrupted regions. It motivates interactive image inpainting which leverages additional hints, e.g., sketches, to assist the inpainting process. Sketch is simple and intuitive to end users, but meanwhile has free forms with much randomness. Such randomness may confuse the inpainting models, and incur severe artifacts in completed images. To address this problem, we propose a two-stage image inpainting method termed SketchRefiner. In the first stage, we propose using a cross-correlation loss function to robustly calibrate and refine the user-provided sketches in a coarse-to-fine fashion. In the second stage, we learn to extract informative features from the abstracted sketches in the feature space and modulate the inpainting process. We also propose an algorithm to simulate real sketches automatically and build a test protocol with different applications. Experimental results on public datasets demonstrate that SketchRefiner effectively utilizes sketch information and eliminates the artifacts due to the free-form sketches. Our method consistently outperforms the state-of-the-art ones both qualitatively and quantitatively, meanwhile revealing great potential in real-world applications. Our code and dataset are available.

Authors:Shubin Huang, Qiong Wu, Yiyi Zhou, Weijie Chen, Rongsheng Zhang, Xiaoshuai Sun, Rongrong Ji

Abstract: Pre-trained language models (PLMs) have played an increasing role in multimedia research. In terms of vision-language (VL) tasks, they often serve as a language encoder and still require an additional fusion network for VL reasoning, resulting in excessive memory overhead. In this paper, we focus on exploring PLMs as a stand-alone model for VL reasoning tasks. Inspired by the recently popular prompt tuning, we first prove that the processed visual features can be also projected onto the semantic space of PLMs and act as prompt tokens to bridge the gap between single- and multi-modal learning. However, this solution exhibits obvious redundancy in visual information and model inference, and the placement of prompt tokens also greatly affects the final performance. Based on these observations, we further propose a novel transfer learning approach for PLMs, termed Dynamic Visual Prompting (DVP). Concretely, DVP first deploys a cross-attention module to obtain text-related and compact visual prompt tokens, thereby greatly reducing the input length of PLMs. To obtain the optimal placement, we also equip DVP with a reinforcement-learning based search algorithm, which can automatically merge DVP with PLMs for different VL tasks via a very short search process. In addition, we also experiment DVP with the recently popular adapter approach to keep the most parameters of PLMs intact when adapting to VL tasks, helping PLMs achieve a quick shift between single- and multi-modal tasks. We apply DVP to two representative PLMs, namely BERT and T5, and conduct extensive experiments on a set of VL reasoning benchmarks including VQA2.0, GQA and SNLIVE. The experimental results not only show the advantage of DVP on efficiency and performance, but also confirm its superiority in adapting pre-trained language models to VL tasks.

Authors:Yi Shi, Jingbo Wang, Xuekun Jiang, Bo Dai

Abstract: Generating realistic and controllable motions for virtual characters is a challenging task in computer animation, and its implications extend to games, simulations, and virtual reality. Recent studies have drawn inspiration from the success of diffusion models in image generation, demonstrating the potential for addressing this task. However, the majority of these studies have been limited to offline applications that target at sequence-level generation that generates all steps simultaneously. To enable real-time motion synthesis with diffusion models in response to time-varying control signals, we propose the framework of the Controllable Motion Diffusion Model (COMODO). Our framework begins with an auto-regressive motion diffusion model (A-MDM), which generates motion sequences step by step. In this way, simply using the standard DDPM algorithm without any additional complexity, our framework is able to generate high-fidelity motion sequences over extended periods with different types of control signals. Then, we propose our reinforcement learning-based controller and controlling strategies on top of the A-MDM model, so that our framework can steer the motion synthesis process across multiple tasks, including target reaching, joystick-based control, goal-oriented control, and trajectory following. The proposed framework enables the real-time generation of diverse motions that react adaptively to user commands on-the-fly, thereby enhancing the overall user experience. Besides, it is compatible with the inpainting-based editing methods and can predict much more diverse motions without additional fine-tuning of the basic motion generation models. We conduct comprehensive experiments to evaluate the effectiveness of our framework in performing various tasks and compare its performance against state-of-the-art methods.

Authors:Linhui Dai, Hong Liu, Pinhao Song, Hao Tang, Runwei Ding, Shengquan Li

Abstract: Underwater object detection (UOD) is crucial for marine economic development, environmental protection, and the planet's sustainable development. The main challenges of this task arise from low-contrast, small objects, and mimicry of aquatic organisms. The key to addressing these challenges is to focus the model on obtaining more discriminative information. We observe that the edges of underwater objects are highly unique and can be distinguished from low-contrast or mimicry environments based on their edges. Motivated by this observation, we propose an Edge-guided Representation Learning Network, termed ERL-Net, that aims to achieve discriminative representation learning and aggregation under the guidance of edge cues. Firstly, we introduce an edge-guided attention module to model the explicit boundary information, which generates more discriminative features. Secondly, a feature aggregation module is proposed to aggregate the multi-scale discriminative features by regrouping them into three levels, effectively aggregating global and local information for locating and recognizing underwater objects. Finally, we propose a wide and asymmetric receptive field block to enable features to have a wider receptive field, allowing the model to focus on more small object information. Comprehensive experiments on three challenging underwater datasets show that our method achieves superior performance on the UOD task.

Authors:Jun Chen, Deyao Zhu, Guocheng Qian, Bernard Ghanem, Zhicheng Yan, Chenchen Zhu, Fanyi Xiao, Mohamed Elhoseiny, Sean Chang Culatana

Abstract: Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches often rely on expensive human annotations as supervision for model training, limiting their scalability to large, unlabeled datasets. To address this challenge, we present ZeroSeg, a novel method that leverages the existing pretrained vision-language (VL) model (e.g. CLIP) to train open-vocabulary zero-shot semantic segmentation models. Although acquired extensive knowledge of visual concepts, it is non-trivial to exploit knowledge from these VL models to the task of semantic segmentation, as they are usually trained at an image level. ZeroSeg overcomes this by distilling the visual concepts learned by VL models into a set of segment tokens, each summarizing a localized region of the target image. We evaluate ZeroSeg on multiple popular segmentation benchmarks, including PASCAL VOC 2012, PASCAL Context, and COCO, in a zero-shot manner (i.e., no training or adaption on target segmentation datasets). Our approach achieves state-of-the-art performance when compared to other zero-shot segmentation methods under the same training data, while also performing competitively compared to strongly supervised methods. Finally, we also demonstrated the effectiveness of ZeroSeg on open-vocabulary segmentation, through both human studies and qualitative visualizations.

Authors:Zhenghang Yuan, Lichao Mou, Xiao Xiang Zhu

Abstract: The Visual Question Answering (VQA) system offers a user-friendly interface and enables human-computer interaction. However, VQA models commonly face the challenge of language bias, resulting from the learned superficial correlation between questions and answers. To address this issue, in this study, we present a novel framework to reduce the language bias of the VQA for remote sensing data (RSVQA). Specifically, we add an adversarial branch to the original VQA framework. Based on the adversarial branch, we introduce two regularizers to constrain the training process against language bias. Furthermore, to evaluate the performance in terms of language bias, we propose a new metric that combines standard accuracy with the performance drop when incorporating question and random image information. Experimental results demonstrate the effectiveness of our method. We believe that our method can shed light on future work for reducing language bias on the RSVQA task.

Authors:Ayan Das, Stathi Fotiadis, Anil Batra, Farhang Nabiei, FengTing Liao, Sattar Vakili, Da-shan Shiu, Alberto Bernacchia

Abstract: The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently, a few studies introduced alternative ways of corrupting images in Diffusion Models, with an emphasis on blurring. However, these studies are purely empirical and it remains unclear what is the optimal procedure for corrupting an image. In this work, we hypothesize that the optimal procedure minimizes the length of the path taken when corrupting an image towards a given final state. We propose the Fisher metric for the path length, measured in the space of probability distributions. We compute the shortest path according to this metric, and we show that it corresponds to a combination of image sharpening, rather than blurring, and noise deblurring. While the corruption was chosen arbitrarily in previous work, our Shortest Path Diffusion (SPD) determines uniquely the entire spatiotemporal structure of the corruption. We show that SPD improves on strong baselines without any hyperparameter tuning, and outperforms all previous Diffusion Models based on image blurring. Furthermore, any small deviation from the shortest path leads to worse performance, suggesting that SPD provides the optimal procedure to corrupt images. Our work sheds new light on observations made in recent works and provides a new approach to improve diffusion models on images and other types of data.

Authors:Xiaoliang Ju, Zhaoyang Huang, Yijin Li, Guofeng Zhang, Yu Qiao, Hongsheng Li

Abstract: We present DiffRoom, a novel framework for tackling the problem of high-quality 3D indoor room reconstruction and generation, both of which are challenging due to the complexity and diversity of the room geometry. Although diffusion-based generative models have previously demonstrated impressive performance in image generation and object-level 3D generation, they have not yet been applied to room-level 3D generation due to their computationally intensive costs. In DiffRoom, we propose a sparse 3D diffusion network that is efficient and possesses strong generative performance for Truncated Signed Distance Field (TSDF), based on a rough occupancy prior. Inspired by KinectFusion's incremental alignment and fusion of local SDFs, we propose a diffusion-based TSDF fusion approach that iteratively diffuses and fuses TSDFs, facilitating the reconstruction and generation of an entire room environment. Additionally, to ease training, we introduce a curriculum diffusion learning paradigm that speeds up the training convergence process and enables high-quality reconstruction. According to the user study, the mesh quality generated by our DiffRoom can even outperform the ground truth mesh provided by ScanNet.

Authors:Yingzhi Zhang, Taiguo Li, Chao Li, Xinghong Zhou

Abstract: Driver distraction causes a significant number of traffic accidents every year, resulting in economic losses and casualties. Currently, the level of automation in commercial vehicles is far from completely unmanned, and drivers still play an important role in operating and controlling the vehicle. Therefore, driver distraction behavior detection is crucial for road safety. At present, driver distraction detection primarily relies on traditional Convolutional Neural Networks (CNN) and supervised learning methods. However, there are still challenges such as the high cost of labeled datasets, limited ability to capture high-level semantic information, and weak generalization performance. In order to solve these problems, this paper proposes a new self-supervised learning method based on masked image modeling for driver distraction behavior detection. Firstly, a self-supervised learning framework for masked image modeling (MIM) is introduced to solve the serious human and material consumption issues caused by dataset labeling. Secondly, the Swin Transformer is employed as an encoder. Performance is enhanced by reconfiguring the Swin Transformer block and adjusting the distribution of the number of window multi-head self-attention (W-MSA) and shifted window multi-head self-attention (SW-MSA) detection heads across all stages, which leads to model more lightening. Finally, various data augmentation strategies are used along with the best random masking strategy to strengthen the model's recognition and generalization ability. Test results on a large-scale driver distraction behavior dataset show that the self-supervised learning method proposed in this paper achieves an accuracy of 99.60%, approximating the excellent performance of advanced supervised learning methods.

Authors:Mohit Mendiratta. Xingang Pan, Mohamed Elgharib, Kartik Teotia, Mallikarjun B R, Ayush Tewari, Vladislav Golyanik, Adam Kortylewski, Christian Theobalt

Abstract: Capturing and editing full head performances enables the creation of virtual characters with various applications such as extended reality and media production. The past few years witnessed a steep rise in the photorealism of human head avatars. Such avatars can be controlled through different input data modalities, including RGB, audio, depth, IMUs and others. While these data modalities provide effective means of control, they mostly focus on editing the head movements such as the facial expressions, head pose and/or camera viewpoint. In this paper, we propose AvatarStudio, a text-based method for editing the appearance of a dynamic full head avatar. Our approach builds on existing work to capture dynamic performances of human heads using neural radiance field (NeRF) and edits this representation with a text-to-image diffusion model. Specifically, we introduce an optimization strategy for incorporating multiple keyframes representing different camera viewpoints and time stamps of a video performance into a single diffusion model. Using this personalized diffusion model, we edit the dynamic NeRF by introducing view-and-time-aware Score Distillation Sampling (VT-SDS) following a model-based guidance approach. Our method edits the full head in a canonical space, and then propagates these edits to remaining time steps via a pretrained deformation network. We evaluate our method visually and numerically via a user study, and results show that our method outperforms existing approaches. Our experiments validate the design choices of our method and highlight that our edits are genuine, personalized, as well as 3D- and time-consistent.

Authors:Siyu Ren, Junhui Hou

Abstract: Quantifying the dissimilarity between two unstructured 3D point clouds is a challenging task, with existing metrics often relying on measuring the distance between corresponding points that can be either inefficient or ineffective. In this paper, we propose a novel distance metric called Calibrated Local Geometry Distance (CLGD), which computes the difference between the underlying 3D surfaces calibrated and induced by a set of reference points. By associating each reference point with two given point clouds through computing its directional distances to them, the difference in directional distances of an identical reference point characterizes the geometric difference between a typical local region of the two point clouds. Finally, CLGD is obtained by averaging the directional distance differences of all reference points. We evaluate CLGD on various optimization and unsupervised learning-based tasks, including shape reconstruction, rigid registration, scene flow estimation, and feature representation. Extensive experiments show that CLGD achieves significantly higher accuracy under all tasks in a memory and computationally efficient manner, compared with existing metrics. As a generic metric, CLGD has the potential to advance 3D point cloud modeling. The source code is publicly available at https://github.com/rsy6318/CLGD.

Authors:Rishubh Parihar, Raghav Magazine, Piyush Tiwari, R. Venkatesh Babu

Abstract: Real-world objects perform complex motions that involve multiple independent motion components. For example, while talking, a person continuously changes their expressions, head, and body pose. In this work, we propose a novel method to decompose motion in videos by using a pretrained image GAN model. We discover disentangled motion subspaces in the latent space of widely used style-based GAN models that are semantically meaningful and control a single explainable motion component. The proposed method uses only a few $(\approx10)$ ground truth video sequences to obtain such subspaces. We extensively evaluate the disentanglement properties of motion subspaces on face and car datasets, quantitatively and qualitatively. Further, we present results for multiple downstream tasks such as motion editing, and selective motion transfer, e.g. transferring only facial expressions without training for it.

Authors:Jun Chen, Ming Hu, Darren J. Coker, Michael L. Berumen, Blair Costelloe, Sara Beery, Anna Rohrbach, Mohamed Elhoseiny

Abstract: Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammal-net.github.io.

Authors:Tongyan Hua, Haotian Bai, Zidong Cao, Lin Wang

Abstract: In this paper, we introduce FMapping, an efficient neural field mapping framework that facilitates the continuous estimation of a colorized point cloud map in real-time dense RGB SLAM. To achieve this challenging goal without depth, a hurdle is how to improve efficiency and reduce the mapping uncertainty of the RGB SLAM system. To this end, we first build up a theoretical analysis by decomposing the SLAM system into tracking and mapping parts, and the mapping uncertainty is explicitly defined within the frame of neural representations. Based on the analysis, we then propose an effective factorization scheme for scene representation and introduce a sliding window strategy to reduce the uncertainty for scene reconstruction. Specifically, we leverage the factorized neural field to decompose uncertainty into a lower-dimensional space, which enhances robustness to noise and improves training efficiency. We then propose the sliding window sampler to reduce uncertainty by incorporating coherent geometric cues from observed frames during map initialization to enhance convergence. Our factorized neural mapping approach enjoys some advantages, such as low memory consumption, more efficient computation, and fast convergence during map initialization. Experiments on two benchmark datasets show that our method can update the map of high-fidelity colorized point clouds around 2 seconds in real time while requiring no customized CUDA kernels. Additionally, it utilizes x20 fewer parameters than the most concise neural implicit mapping of prior methods for SLAM, e.g., iMAP [ 31] and around x1000 fewer parameters than the state-of-the-art approach, e.g., NICE-SLAM [ 42]. For more details, please refer to our project homepage: https://vlis2022.github.io/fmap/.

Authors:Yingying Fan, Yu Wu, Yutian Lin, Bo Du

Abstract: We focus on the weakly-supervised audio-visual video parsing task (AVVP), which aims to identify and locate all the events in audio/visual modalities. Previous works only concentrate on video-level overall label denoising across modalities, but overlook the segment-level label noise, where adjacent video segments (i.e., 1-second video clips) may contain different events. However, recognizing events in the segment is challenging because its label could be any combination of events that occur in the video. To address this issue, we consider tackling AVVP from the language perspective, since language could freely describe how various events appear in each segment beyond fixed labels. Specifically, we design language prompts to describe all cases of event appearance for each video. Then, the similarity between language prompts and segments is calculated, where the event of the most similar prompt is regarded as the segment-level label. In addition, to deal with the mislabeled segments, we propose to perform dynamic re-weighting on the unreliable segments to adjust their labels. Experiments show that our simple yet effective approach outperforms state-of-the-art methods by a large margin.

Authors:Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao

Abstract: It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on different tasks or benchmarks. Previous works mainly focus on the self-supervised pre-training pipeline, meaning that they perform the pre-training and fine-tuning on the same benchmark, which is difficult to attain the performance scalability and cross-dataset application for the pre-training checkpoint. In this paper, for the first time, we are committed to building a large-scale pre-training point-cloud dataset with diverse data distribution, and meanwhile learning generalizable representations from such a diverse pre-training dataset. We formulate the point-cloud pre-training task as a semi-supervised problem, which leverages the few-shot labeled and massive unlabeled point-cloud data to generate the unified backbone representations that can be directly applied to many baseline models and benchmarks, decoupling the AD-related pre-training process and downstream fine-tuning task. During the period of backbone pre-training, by enhancing the scene- and instance-level distribution diversity and exploiting the backbone's ability to learn from unknown instances, we achieve significant performance gains on a series of downstream perception benchmarks including Waymo, nuScenes, and KITTI, under different baseline models like PV-RCNN++, SECOND, CenterPoint.

Authors:Alexandru Ghita, Radu Tudor Ionescu

Abstract: The performance of neural networks in content-based image retrieval (CBIR) is highly influenced by the chosen loss (objective) function. The majority of objective functions for neural models can be divided into metric learning and statistical learning. Metric learning approaches require a pair mining strategy that often lacks efficiency, while statistical learning approaches are not generating highly compact features due to their indirect feature optimization. To this end, we propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimizes for the L2 metric without the need of generating pairs. Our loss is formed of three components. One leading objective ensures that the learned features are attracted to each designated learnable class anchor. The second loss component regulates the anchors and forces them to be separable by a margin, while the third objective ensures that the anchors do not collapse to zero. Furthermore, we develop a more efficient two-stage retrieval system by harnessing the learned class anchors during the first stage of the retrieval process, eliminating the need of comparing the query with every image in the database. We establish a set of four datasets (CIFAR-100, Food-101, SVHN, and Tiny ImageNet) and evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures. Compared to existing objective functions, our empirical evidence shows that the proposed objective is generating superior and more consistent results.

Authors:Pablo Pernias, Dominic Rampas, Marc Aubreville

Abstract: We introduce Wuerstchen, a novel technique for text-to-image synthesis that unites competitive performance with unprecedented cost-effectiveness and ease of training on constrained hardware. Building on recent advancements in machine learning, our approach, which utilizes latent diffusion strategies at strong latent image compression rates, significantly reduces the computational burden, typically associated with state-of-the-art models, while preserving, if not enhancing, the quality of generated images. Wuerstchen achieves notable speed improvements at inference time, thereby rendering real-time applications more viable. One of the key advantages of our method lies in its modest training requirements of only 9,200 GPU hours, slashing the usual costs significantly without compromising the end performance. In a comparison against the state-of-the-art, we found the approach to yield strong competitiveness. This paper opens the door to a new line of research that prioritizes both performance and computational accessibility, hence democratizing the use of sophisticated AI technologies. Through Wuerstchen, we demonstrate a compelling stride forward in the realm of text-to-image synthesis, offering an innovative path to explore in future research.

Authors:Sebastian Hafner, Yifang Ban

Abstract: This paper proposes a novel multi-temporal urban mapping approach using multi-modal satellite data from the Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Instrument (MSI) missions. In particular, it focuses on the problem of a partly missing optical modality due to clouds. The proposed model utilizes two networks to extract features from each modality separately. In addition, a reconstruction network is utilized to approximate the optical features based on the SAR data in case of a missing optical modality. Our experiments on a multi-temporal urban mapping dataset with Sentinel-1 SAR and Sentinel-2 MSI data demonstrate that the proposed method outperforms a multi-modal approach that uses zero values as a replacement for missing optical data, as well as a uni-modal SAR-based approach. Therefore, the proposed method is effective in exploiting multi-modal data, if available, but it also retains its effectiveness in case the optical modality is missing.

Authors:Robert A. Marsden, Mario Döbler, Bin Yang

Abstract: Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data. Clearly, a method proposed for online TTA has to perform well for all kinds of environmental conditions. By introducing the variable factors 'domain non-stationarity' and 'temporal correlation', we first unfold all practically relevant settings and define the entity as universal TTA. To tackle the problem of universal TTA, we identify and highlight several challenges a self-training based method has to deal with, including: 1) model bias and the occurrence of trivial solutions when performing entropy minimization on varying sequence lengths with and without multiple domain shifts, 2) loss of generalization which exacerbates the adaptation to future domain shifts and the occurrence of catastrophic forgetting, and 3) performance degradation due to shifts in label prior. To prevent the model from becoming biased, we leverage a dataset and model-agnostic certainty and diversity weighting. In order to maintain generalization and prevent catastrophic forgetting, we propose to continually weight-average the source and adapted model. To compensate for disparities in the label prior during test-time, we propose an adaptive additive prior correction scheme. We evaluate our approach, named ROID, on a wide range of settings, datasets, and models, setting new standards in the field of universal TTA.

Authors:Qijian Zhang, Junhui Hou, Yohanes Yudhi Adikusuma, Wenping Wang, Ying He

Abstract: Geodesics are essential in many geometry processing applications. However, traditional algorithms for computing geodesic distances and paths on 3D mesh models are often inefficient and slow. This makes them impractical for scenarios that require extensive querying of arbitrary point-to-point geodesics. Although neural implicit representations have emerged as a popular way of representing 3D shape geometries, there is still no research on representing geodesics with deep implicit functions. To bridge this gap, this paper presents the first attempt to represent geodesics on 3D mesh models using neural implicit functions. Specifically, we introduce neural geodesic fields (NeuroGFs), which are learned to represent the all-pairs geodesics of a given mesh. By using NeuroGFs, we can efficiently and accurately answer queries of arbitrary point-to-point geodesic distances and paths, overcoming the limitations of traditional algorithms. Evaluations on common 3D models show that NeuroGFs exhibit exceptional performance in solving the single-source all-destination (SSAD) and point-to-point geodesics, and achieve high accuracy consistently. Moreover, NeuroGFs offer the unique advantage of encoding both 3D geometry and geodesics in a unified representation. Code is made available at https://github.com/keeganhk/NeuroGF/tree/master.

Authors:Dunbin Shen, Xiaorui Ma, Wenfeng Kong, Jiacheng Tian, Hongyu Wang

Abstract: Hyperspectral target detection is good at finding dim and small objects based on spectral characteristics. However, existing representation-based methods are hindered by the problem of the unknown background dictionary and insufficient utilization of spatial information. To address these issues, this paper proposes an efficient optimizing approach based on low-rank representation (LRR) and graph Laplacian regularization (GLR). Firstly, to obtain a complete and pure background dictionary, we propose a LRR-based background subspace learning method by jointly mining the low-dimensional structure of all pixels. Secondly, to fully exploit local spatial relationships and capture the underlying geometric structure, a local region-based GLR is employed to estimate the coefficients. Finally, the desired detection map is generated by computing the ratio of representation errors from binary hypothesis testing. The experiments conducted on two benchmark datasets validate the effectiveness and superiority of the approach. For reproduction, the accompanying code is available at https://github.com/shendb2022/LRBSL-GLR.

Authors:Ning Ding, Yehui Tang, Zhongqian Fu, Chao Xu, Kai Han, Yunhe Wang

Abstract: The recent upsurge in pre-trained large models (e.g. GPT-4) has swept across the entire deep learning community. Such powerful large language models (LLMs) demonstrate advanced generative ability and multimodal understanding capability, which quickly achieve new state-of-the-art performances on a variety of benchmarks. The pre-trained LLM usually plays the role as a universal AI model that can conduct various tasks, including context reasoning, article analysis and image content comprehension. However, considering the prohibitively high memory and computational cost for implementing such a large model, the conventional models (such as CNN and ViT), are still essential for many visual perception tasks. In this paper, we propose to enhance the representation ability of ordinary vision models for perception tasks (e.g. image classification) by taking advantage of large pre-trained models. We present a new learning paradigm in which the knowledge extracted from large pre-trained models are utilized to help models like CNN and ViT learn enhanced representations and achieve better performance. Firstly, we curate a high quality description set by prompting a multimodal LLM to generate descriptive text for all training images. Furthermore, we feed these detailed descriptions into a pre-trained encoder to extract text embeddings with rich semantic information that encodes the content of images. During training, text embeddings will serve as extra supervising signals and be aligned with image representations learned by vision models. The alignment process helps vision models learn better and achieve higher accuracy with the assistance of pre-trained LLMs. We conduct extensive experiments to verify that the proposed algorithm consistently improves the performance for various vision models with heterogeneous architectures.

Authors:Lukas Radl, Andreas Kurz, Markus Steinberger

Abstract: Modern Neural Radiance Fields (NeRFs) learn a mapping from position to volumetric density via proposal network samplers. In contrast to the coarse-to-fine sampling approach with two NeRFs, this offers significant potential for speedups using lower network capacity as the task of mapping spatial coordinates to volumetric density involves no view-dependent effects and is thus much easier to learn. Given that most of the network capacity is utilized to estimate radiance, NeRFs could store valuable density information in their parameters or their deep features. To this end, we take one step back and analyze large, trained ReLU-MLPs used in coarse-to-fine sampling. We find that trained NeRFs, Mip-NeRFs and proposal network samplers map samples with high density to local minima along a ray in activation feature space. We show how these large MLPs can be accelerated by transforming the intermediate activations to a weight estimate, without any modifications to the parameters post-optimization. With our approach, we can reduce the computational requirements of trained NeRFs by up to 50% with only a slight hit in rendering quality and no changes to the training protocol or architecture. We evaluate our approach on a variety of architectures and datasets, showing that our proposition holds in various settings.

Authors:Tamer Saleh, Xingxing Weng, Shimaa Holail, Chen Hao, Gui-Song Xia

Abstract: The detection of flooded areas using high-resolution synthetic aperture radar (SAR) imagery is a critical task with applications in crisis and disaster management, as well as environmental resource planning. However, the complex nature of SAR images presents a challenge that often leads to an overestimation of the flood extent. To address this issue, we propose a novel differential attention metric-based network (DAM-Net) in this study. The DAM-Net comprises two key components: a weight-sharing Siamese backbone to obtain multi-scale change features of multi-temporal images and tokens containing high-level semantic information of water-body changes, and a temporal differential fusion (TDF) module that integrates semantic tokens and change features to generate flood maps with reduced speckle noise. Specifically, the backbone is split into multiple stages. In each stage, we design three modules, namely, temporal-wise feature extraction (TWFE), cross-temporal change attention (CTCA), and temporal-aware change enhancement (TACE), to effectively extract the change features. In TACE of the last stage, we introduce a class token to record high-level semantic information of water-body changes via the attention mechanism. Another challenge faced by data-driven deep learning algorithms is the limited availability of flood detection datasets. To overcome this, we have created the S1GFloods open-source dataset, a global-scale high-resolution Sentinel-1 SAR image pairs dataset covering 46 global flood events between 2015 and 2022. The experiments on the S1GFloods dataset using the proposed DAM-Net showed top results compared to state-of-the-art methods in terms of overall accuracy, F1-score, and IoU, which reached 97.8%, 96.5%, and 93.2%, respectively. Our dataset and code will be available online at https://github.com/Tamer-Saleh/S1GFlood-Detection.

Authors:Ruibin Li, Qihua Zhou, Song Guo, Jie Zhang, Jingcai Guo, Xinyang Jiang, Yifei Shen, Zhenhua Han

Abstract: Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content, opening up the opportunity to improve image super-resolution (SR) tasks. Recent solutions for these tasks often train architecture-specific DGMs from scratch, or require iterative fine-tuning and distillation on pre-trained DGMs, both of which take considerable time and hardware investments. More seriously, since the DGMs are established with a discrete pre-defined upsampling scale, they cannot well match the emerging requirements of arbitrary-scale super-resolution (ASSR), where a unified model adapts to arbitrary upsampling scales, instead of preparing a series of distinct models for each case. These limitations beg an intriguing question: can we identify the ASSR capability of existing pre-trained DGMs without the need for distillation or fine-tuning? In this paper, we take a step towards resolving this matter by proposing Diff-SR, a first ASSR attempt based solely on pre-trained DGMs, without additional training efforts. It is motivated by an exciting finding that a simple methodology, which first injects a specific amount of noise into the low-resolution images before invoking a DGM's backward diffusion process, outperforms current leading solutions. The key insight is determining a suitable amount of noise to inject, i.e., small amounts lead to poor low-level fidelity, while over-large amounts degrade the high-level signature. Through a finely-grained theoretical analysis, we propose the Perceptual Recoverable Field (PRF), a metric that achieves the optimal trade-off between these two factors. Extensive experiments verify the effectiveness, flexibility, and adaptability of Diff-SR, demonstrating superior performance to state-of-the-art solutions under diverse ASSR environments.

Authors:Alvaro Gonzalez-Jimenez, Simone Lionetti, Philippe Gottfrois, Fabian Gröger, Marc Pouly, Alexander Navarini

Abstract: This paper presents a new robust loss function, the T-Loss, for medical image segmentation. The proposed loss is based on the negative log-likelihood of the Student-t distribution and can effectively handle outliers in the data by controlling its sensitivity with a single parameter. This parameter is updated during the backpropagation process, eliminating the need for additional computation or prior information about the level and spread of noisy labels. Our experiments show that the T-Loss outperforms traditional loss functions in terms of dice scores on two public medical datasets for skin lesion and lung segmentation. We also demonstrate the ability of T-Loss to handle different types of simulated label noise, resembling human error. Our results provide strong evidence that the T-Loss is a promising alternative for medical image segmentation where high levels of noise or outliers in the dataset are a typical phenomenon in practice. The project website can be found at https://robust-tloss.github.io

Authors:Leonard Hackel Technische Universität Berlin Berlin Institute for the Foundations of Learning and Data, Kai Norman Clasen Technische Universität Berlin, Mahdyar Ravanbakhsh Zalando SE Berlin, Beg/"um Demir Technische Universität Berlin Berlin Institute for the Foundations of Learning and Data

Abstract: Visual question answering (VQA) methods in remote sensing (RS) aim to answer natural language questions with respect to an RS image. Most of the existing methods require a large amount of computational resources, which limits their application in operational scenarios in RS. To address this issue, in this paper we present an effective lightweight transformer-based VQA in RS (LiT-4-RSVQA) architecture for efficient and accurate VQA in RS. Our architecture consists of: i) a lightweight text encoder module; ii) a lightweight image encoder module; iii) a fusion module; and iv) a classification module. The experimental results obtained on a VQA benchmark dataset demonstrate that our proposed LiT-4-RSVQA architecture provides accurate VQA results while significantly reducing the computational requirements on the executing hardware. Our code is publicly available at https://git.tu-berlin.de/rsim/lit4rsvqa.

Authors:Kihyuk Sohn, Albert Shaw, Yuan Hao, Han Zhang, Luisa Polania, Huiwen Chang, Lu Jiang, Irfan Essa

Abstract: We study domain-adaptive image synthesis, the problem of teaching pretrained image generative models a new style or concept from as few as one image to synthesize novel images, to better understand the compositional image synthesis. We present a framework that leverages a pretrained class-conditional generation model and visual prompt tuning. Specifically, we propose a novel source class distilled visual prompt that learns disentangled prompts of semantic (e.g., class) and domain (e.g., style) from a few images. Learned domain prompt is then used to synthesize images of any classes in the style of target domain. We conduct studies on various target domains with the number of images ranging from one to a few to many, and show qualitative results which show the compositional generalization of our method. Moreover, we show that our method can help improve zero-shot domain adaptation classification accuracy.

Authors:Ilya A. Petrov, Riccardo Marin, Julian Chibane, Gerard Pons-Moll

Abstract: The intimate entanglement between objects affordances and human poses is of large interest, among others, for behavioural sciences, cognitive psychology, and Computer Vision communities. In recent years, the latter has developed several object-centric approaches: starting from items, learning pipelines synthesizing human poses and dynamics in a realistic way, satisfying both geometrical and functional expectations. However, the inverse perspective is significantly less explored: Can we infer 3D objects and their poses from human interactions alone? Our investigation follows this direction, showing that a generic 3D human point cloud is enough to pop up an unobserved object, even when the user is just imitating a functionality (e.g., looking through a binocular) without involving a tangible counterpart. We validate our method qualitatively and quantitatively, with synthetic data and sequences acquired for the task, showing applicability for XR/VR. The code is available at https://github.com/ptrvilya/object-popup.

Authors:Hao Zhang, Yanbo Xu, Tianyuan Dai, Yu-Wing, Tai Chi-Keung Tang

Abstract: The ability to create high-quality 3D faces from a single image has become increasingly important with wide applications in video conferencing, AR/VR, and advanced video editing in movie industries. In this paper, we propose Face Diffusion NeRF (FDNeRF), a new generative method to reconstruct high-quality Face NeRFs from single images, complete with semantic editing and relighting capabilities. FDNeRF utilizes high-resolution 3D GAN inversion and expertly trained 2D latent-diffusion model, allowing users to manipulate and construct Face NeRFs in zero-shot learning without the need for explicit 3D data. With carefully designed illumination and identity preserving loss, as well as multi-modal pre-training, FD-NeRF offers users unparalleled control over the editing process enabling them to create and edit face NeRFs using just single-view images, text prompts, and explicit target lighting. The advanced features of FDNeRF have been designed to produce more impressive results than existing 2D editing approaches that rely on 2D segmentation maps for editable attributes. Experiments show that our FDNeRF achieves exceptionally realistic results and unprecedented flexibility in editing compared with state-of-the-art 3D face reconstruction and editing methods. Our code will be available at https://github.com/BillyXYB/FDNeRF.

Authors:Barış Büyüktaş, Gencer Sumbul, Begüm Demir

Abstract: The development of federated learning (FL) methods, which aim to learn from distributed databases (i.e., clients) without accessing data on clients, has recently attracted great attention. Most of these methods assume that the clients are associated with the same data modality. However, remote sensing (RS) images in different clients can be associated with different data modalities that can improve the classification performance when jointly used. To address this problem, in this paper we introduce a novel multi-modal FL framework that aims to learn from decentralized multi-modal RS image archives for RS image classification problems. The proposed framework is made up of three modules: 1) multi-modal fusion (MF); 2) feature whitening (FW); and 3) mutual information maximization (MIM). The MF module performs iterative model averaging to learn without accessing data on clients in the case that clients are associated with different data modalities. The FW module aligns the representations learned among the different clients. The MIM module maximizes the similarity of images from different modalities. Experimental results show the effectiveness of the proposed framework compared to iterative model averaging, which is a widely used algorithm in FL. The code of the proposed framework is publicly available at https://git.tu-berlin.de/rsim/MM-FL.

Authors:Juan A. Rodriguez, David Vazquez, Issam Laradji, Marco Pedersoli, Pau Rodriguez

Abstract: The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art. Recent techniques have shown impressive potential in creating complex visual compositions while delivering impressive realism and quality. However, state-of-the-art methods have been focusing on the narrow domain of natural images, while other distributions remain unexplored. In this paper, we introduce the problem of text-to-figure generation, that is creating scientific figures of papers from text descriptions. We present FigGen, a diffusion-based approach for text-to-figure as well as the main challenges of the proposed task. Code and models are available at https://github.com/joanrod/figure-diffusion

Authors:Xiao Dong, Runhui Huang, Xiaoyong Wei, Zequn Jie, Jianxing Yu, Jian Yin, Xiaodan Liang

Abstract: Recent advances in vision-language pre-training have enabled machines to perform better in multimodal object discrimination (e.g., image-text semantic alignment) and image synthesis (e.g., text-to-image generation). On the other hand, fine-tuning pre-trained models with discriminative or generative capabilities such as CLIP and Stable Diffusion on domain-specific datasets has shown to be effective in various tasks by adapting to specific domains. However, few studies have explored the possibility of learning both discriminative and generative capabilities and leveraging their synergistic effects to create a powerful and personalized multimodal model during fine-tuning. This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC). UniDiff effectively learns aligned semantics and mitigates the issue of semantic collapse during fine-tuning on small datasets by leveraging RSC on visual features from CLIP and diffusion models, without altering the pre-trained model's basic architecture. UniDiff demonstrates versatility in both multi-modal understanding and generative tasks. Experimental results on three datasets (Fashion-man, Fashion-woman, and E-commercial Product) showcase substantial enhancements in vision-language retrieval and text-to-image generation, illustrating the advantages of combining discriminative and generative fine-tuning. The proposed UniDiff model establishes a robust pipeline for personalized modeling and serves as a benchmark for future comparisons in the field.

Authors:Ruotong Wang, Hongrui Chen, Zihao Zhu, Li Liu, Yong Zhang, Yanbo Fan, Baoyuan Wu

Abstract: Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on normal samples. This type of attack is known as a backdoor attack. Recent research has focused on designing invisible triggers for backdoor attacks to ensure visual stealthiness. These triggers have demonstrated strong attack performance even under backdoor defense, which aims to eliminate or suppress the backdoor effect in the model. However, through experimental observations, we have noticed that these carefully designed invisible triggers are often susceptible to visual distortion during inference, such as Gaussian blurring or environmental variations in real-world scenarios. This phenomenon significantly undermines the effectiveness of attacks in practical applications. Unfortunately, this issue has not received sufficient attention and has not been thoroughly investigated. To address this limitation, we propose a novel approach called the Visible, Semantic, Sample-Specific, and Compatible trigger (VSSC-trigger), which leverages a recent powerful image method known as the stable diffusion model. In this approach, a text trigger is utilized as a prompt and combined with a benign image. The resulting combination is then processed by a pre-trained stable diffusion model, generating a corresponding semantic object. This object is seamlessly integrated with the original image, resulting in a new realistic image, referred to as the poisoned image. Extensive experimental results and analysis validate the effectiveness and robustness of our proposed attack method, even in the presence of visual distortion. We believe that the new trigger proposed in this work, along with the proposed idea to address the aforementioned issues, will have significant prospective implications for further advancements in this direction.

Authors:Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier

Abstract: Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or equivalently their positions, are learnable. Non-integer positions are handled via interpolation. Thanks to this trick, positions have well-defined gradients. The original DCLS used bilinear interpolation, and thus only considered the four nearest pixels. Yet here we show that longer range interpolations, and in particular a Gaussian interpolation, allow improving performance on ImageNet1k classification on two state-of-the-art convolutional architectures (ConvNeXt and Conv\-Former), without increasing the number of parameters. The method code is based on PyTorch and is available at https://github.com/K-H-Ismail/Dilated-Convolution-with-Learnable-Spacings-PyTorch

Authors:Sebastian Bullinger, Florian Fevers, Christoph Bodensteiner, Michael Arens

Abstract: To cope with the high requirements during the computation of semantic segmentations of earth observation imagery, current state-of-the-art pipelines divide the corresponding data into smaller images. Existing methods and benchmark datasets oftentimes rely on pixel-based tiling schemes or on geo-tiling schemes employed by web mapping applications. The selection of the subimages (comprising size, location and orientation) is crucial since it affects the available context information of each pixel, defines the number of tiles during training, and influences the degree of information degradation while down- and up-sampling the tile contents to the size required by the segmentation model. In this paper we propose a new segmentation pipeline for earth observation imagery relying on a tiling scheme that creates geo-tiles based on the geo-information of the raster data. This approach exhibits several beneficial properties compared to pixel-based or common web mapping approaches. For instance, the proposed tiling scheme shows flexible customization properties regarding tile granularity, tile stride and image boundary alignment, which allows us to perform a tile specific data augmentation during training and a substitution of pixel predictions with limited context information using data of overlapping tiles during inference. Furthermore, the generated tiles show a consistent spatial tile extent w.r.t. heterogeneous sensors, varying recording distances and different latitudes. In our experiments we demonstrate how the proposed tiling system allows to improve the results of current state-of-the-art semantic segmentation models. To foster future research we make the source code publicly available.

Authors:Dan Yang, Mehmet Yamac

Abstract: Event cameras differ from conventional RGB cameras in that they produce asynchronous data sequences. While RGB cameras capture every frame at a fixed rate, event cameras only capture changes in the scene, resulting in sparse and asynchronous data output. Despite the fact that event data carries useful information that can be utilized in motion deblurring of RGB cameras, integrating event and image information remains a challenge. Recent state-of-the-art CNN-based deblurring solutions produce multiple 2-D event frames based on the accumulation of event data over a time period. In most of these techniques, however, the number of event frames is fixed and predefined, which reduces temporal resolution drastically, particularly for scenarios when fast-moving objects are present or when longer exposure times are required. It is also important to note that recent modern cameras (e.g., cameras in mobile phones) dynamically set the exposure time of the image, which presents an additional problem for networks developed for a fixed number of event frames. A Long Short-Term Memory (LSTM)-based event feature extraction module has been developed for addressing these challenges, which enables us to use a dynamically varying number of event frames. Using these modules, we constructed a state-of-the-art deblurring network, Deformable Convolutions and LSTM-based Flexible Event Frame Fusion Network (DLEFNet). It is particularly useful for scenarios in which exposure times vary depending on factors such as lighting conditions or the presence of fast-moving objects in the scene. It has been demonstrated through evaluation results that the proposed method can outperform the existing state-of-the-art networks for deblurring task in synthetic and real-world data sets.

Authors:Shreya Shetye, Anwita Maiti, Tannistha Maiti, Tarry Singh

Abstract: Sexual harassment, sexual abuse, and sexual violence are prevalent problems in this day and age. Women's safety is an important issue that needs to be highlighted and addressed. Given this issue, we have studied each of these concerns and the factors that affect it based on images generated from movies. We have classified the three terms (harassment, abuse, and violence) based on the visual attributes present in images depicting these situations. We identified that factors such as facial expression of the victim and perpetrator and unwanted touching had a direct link to identifying the scenes containing sexual harassment, abuse and violence. We also studied and outlined how state-of-the-art explicit content detectors such as Google Cloud Vision API and Clarifai API fail to identify and categorise these images. Based on these definitions and characteristics, we have developed a first-of-its-kind dataset from various Indian movie scenes. These scenes are classified as sexual harassment, sexual abuse, or sexual violence and exported in the PASCAL VOC 1.1 format. Our dataset is annotated on the identified relevant features and can be used to develop and train a deep-learning computer vision model to identify these issues. The dataset is publicly available for research and development.

Authors:Rui Shao, Tianxing Wu, Liqiang Nie, Ziwei Liu

Abstract: Existing deepfake detection methods fail to generalize well to unseen or degraded samples, which can be attributed to the over-fitting of low-level forgery patterns. Here we argue that high-level semantics are also indispensable recipes for generalizable forgery detection. Recently, large pre-trained Vision Transformers (ViTs) have shown promising generalization capability. In this paper, we propose the first parameter-efficient tuning approach for deepfake detection, namely DeepFake-Adapter, to effectively and efficiently adapt the generalizable high-level semantics from large pre-trained ViTs to aid deepfake detection. Given large pre-trained models but limited deepfake data, DeepFake-Adapter introduces lightweight yet dedicated dual-level adapter modules to a ViT while keeping the model backbone frozen. Specifically, to guide the adaptation process to be aware of both global and local forgery cues of deepfake data, 1) we not only insert Globally-aware Bottleneck Adapters in parallel to MLP layers of ViT, 2) but also actively cross-attend Locally-aware Spatial Adapters with features from ViT. Unlike existing deepfake detection methods merely focusing on low-level forgery patterns, the forgery detection process of our model can be regularized by generalizable high-level semantics from a pre-trained ViT and adapted by global and local low-level forgeries of deepfake data. Extensive experiments on several standard deepfake detection benchmarks validate the effectiveness of our approach. Notably, DeepFake-Adapter demonstrates a convincing advantage under cross-dataset and cross-manipulation settings. The source code is released at https://github.com/rshaojimmy/DeepFake-Adapter

Authors:Hong-Yu Zhou, Yizhou Yu, Chengdi Wang, Shu Zhang, Yuanxu Gao, Jia Pan, Jun Shao, Guangming Lu, Kang Zhang, Weimin Li

Abstract: During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results. Deep-learning models for aiding diagnosis have yet to meet this requirement. Here we report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model uses embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and bidirectional blocks with intramodal and intermodal attention to learn a holistic representation of radiographs, the unstructured chief complaint and clinical history, structured clinical information such as laboratory-test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Leveraging unified multimodal Transformer-based models may help streamline triage of patients and facilitate the clinical decision process.

Authors:Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, Jianfeng Gao

Abstract: Conversational generative AI has demonstrated remarkable promise for empowering biomedical practitioners, but current investigations focus on unimodal text. Multimodal conversational AI has seen rapid progress by leveraging billions of image-text pairs from the public web, but such general-domain vision-language models still lack sophistication in understanding and conversing about biomedical images. In this paper, we propose a cost-efficient approach for training a vision-language conversational assistant that can answer open-ended research questions of biomedical images. The key idea is to leverage a large-scale, broad-coverage biomedical figure-caption dataset extracted from PubMed Central, use GPT-4 to self-instruct open-ended instruction-following data from the captions, and then fine-tune a large general-domain vision-language model using a novel curriculum learning method. Specifically, the model first learns to align biomedical vocabulary using the figure-caption pairs as is, then learns to master open-ended conversational semantics using GPT-4 generated instruction-following data, broadly mimicking how a layperson gradually acquires biomedical knowledge. This enables us to train a Large Language and Vision Assistant for BioMedicine (LLaVA-Med) in less than 15 hours (with eight A100s). LLaVA-Med exhibits excellent multimodal conversational capability and can follow open-ended instruction to assist with inquiries about a biomedical image. On three standard biomedical visual question answering datasets, LLaVA-Med outperforms previous supervised state-of-the-art on certain metrics. To facilitate biomedical multimodal research, we will release our instruction-following data and the LLaVA-Med model.

Authors:Pamuditha Somarathne, Tharindu Wickremasinghe, Amashi Niwarthana, A. Thieshanthan, Chamira U. S. Edussooriya, Dushan N. Wadduwage

Abstract: Compressive sensing (CS) reconstructs images from sub-Nyquist measurements by solving a sparsity-regularized inverse problem. Traditional CS solvers use iterative optimizers with hand crafted sparsifiers, while early data-driven methods directly learn an inverse mapping from the low-dimensional measurement space to the original image space. The latter outperforms the former, but is restrictive to a pre-defined measurement domain. More recent, deep unrolling methods combine traditional proximal gradient methods and data-driven approaches to iteratively refine an image approximation. To achieve higher accuracy, it has also been suggested to learn both the sampling matrix, and the choice of measurement vectors adaptively. Contrary to the current trend, in this work we hypothesize that a general inverse mapping from a random set of compressed measurements to the image domain exists for a given measurement basis, and can be learned. Such a model is single-shot, non-restrictive and does not parametrize the sampling process. To this end, we propose MOSAIC, a novel compressive sensing framework to reconstruct images given any random selection of measurements, sampled using a fixed basis. Motivated by the uneven distribution of information across measurements, MOSAIC incorporates an embedding technique to efficiently apply attention mechanisms on an encoded sequence of measurements, while dispensing the need to use unrolled deep networks. A range of experiments validate our proposed architecture as a promising alternative for existing CS reconstruction methods, by achieving the state-of-the-art for metrics of reconstruction accuracy on standard datasets.

Authors:Nico Giambi, Giuseppe Lisanti

Abstract: Deep generative models have shown impressive results in generating realistic images of faces. GANs managed to generate high-quality, high-fidelity images when conditioned on semantic masks, but they still lack the ability to diversify their output. Diffusion models partially solve this problem and are able to generate diverse samples given the same condition. In this paper, we propose a multi-conditioning approach for diffusion models via cross-attention exploiting both attributes and semantic masks to generate high-quality and controllable face images. We also studied the impact of applying perceptual-focused loss weighting into the latent space instead of the pixel space. Our method extends the previous approaches by introducing conditioning on more than one set of features, guaranteeing a more fine-grained control over the generated face images. We evaluate our approach on the CelebA-HQ dataset, and we show that it can generate realistic and diverse samples while allowing for fine-grained control over multiple attributes and semantic regions. Additionally, we perform an ablation study to evaluate the impact of different conditioning strategies on the quality and diversity of the generated images.

Authors:Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, Elisa Ricci

Abstract: Recent advances in large vision-language models have revolutionized the image classification paradigm. Despite showing impressive zero-shot capabilities, a pre-defined set of categories, a.k.a. the vocabulary, is assumed at test time for composing the textual prompts. However, such assumption can be impractical when the semantic context is unknown and evolving. We thus formalize a novel task, termed as Vocabulary-free Image Classification (VIC), where we aim to assign to an input image a class that resides in an unconstrained language-induced semantic space, without the prerequisite of a known vocabulary. VIC is a challenging task as the semantic space is extremely large, containing millions of concepts, with hard-to-discriminate fine-grained categories. In this work, we first empirically verify that representing this semantic space by means of an external vision-language database is the most effective way to obtain semantically relevant content for classifying the image. We then propose Category Search from External Databases (CaSED), a method that exploits a pre-trained vision-language model and an external vision-language database to address VIC in a training-free manner. CaSED first extracts a set of candidate categories from captions retrieved from the database based on their semantic similarity to the image, and then assigns to the image the best matching candidate category according to the same vision-language model. Experiments on benchmark datasets validate that CaSED outperforms other complex vision-language frameworks, while being efficient with much fewer parameters, paving the way for future research in this direction.

Authors:Ge Yuan, Xiaodong Cun, Yong Zhang, Maomao Li, Chenyang Qi, Xintao Wang, Ying Shan, Huicheng Zheng

Abstract: Exquisite demand exists for customizing the pretrained large text-to-image model, $\textit{e.g.}$, Stable Diffusion, to generate innovative concepts, such as the users themselves. However, the newly-added concept from previous customization methods often shows weaker combination abilities than the original ones even given several images during training. We thus propose a new personalization method that allows for the seamless integration of a unique individual into the pre-trained diffusion model using just $\textbf{one facial photograph}$ and only $\textbf{1024 learnable parameters}$ under $\textbf{3 minutes}$. So as we can effortlessly generate stunning images of this person in any pose or position, interacting with anyone and doing anything imaginable from text prompts. To achieve this, we first analyze and build a well-defined celeb basis from the embedding space of the pre-trained large text encoder. Then, given one facial photo as the target identity, we generate its own embedding by optimizing the weight of this basis and locking all other parameters. Empowered by the proposed celeb basis, the new identity in our customized model showcases a better concept combination ability than previous personalization methods. Besides, our model can also learn several new identities at once and interact with each other where the previous customization model fails to. The code will be released.

Authors:Abisek Rajakumar Kalarani, Pushpak Bhattacharyya, Niyati Chhaya, Sumit Shekhar

Abstract: Well-formed context aware image captions and tags in enterprise content such as marketing material are critical to ensure their brand presence and content recall. Manual creation and updates to ensure the same is non trivial given the scale and the tedium towards this task. We propose a new unified Vision-Language (VL) model based on the One For All (OFA) model, with a focus on context-assisted image captioning where the caption is generated based on both the image and its context. Our approach aims to overcome the context-independent (image and text are treated independently) nature of the existing approaches. We exploit context by pretraining our model with datasets of three tasks: news image captioning where the news article is the context, contextual visual entailment, and keyword extraction from the context. The second pretraining task is a new VL task, and we construct and release two datasets for the task with 1.1M and 2.2K data instances. Our system achieves state-of-the-art results with an improvement of up to 8.34 CIDEr score on the benchmark news image captioning datasets. To the best of our knowledge, ours is the first effort at incorporating contextual information in pretraining the models for the VL tasks.

Authors:Jinbo Xing, Menghan Xia, Yuxin Liu, Yuechen Zhang, Yong Zhang, Yingqing He, Hanyuan Liu, Haoxin Chen, Xiaodong Cun, Xintao Wang, Ying Shan, Tien-Tsin Wong

Abstract: Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. While text is convenient in conveying the overall scene context, it may be insufficient to control precisely. In this paper, we explore customized video generation by utilizing text as context description and motion structure (e.g. frame-wise depth) as concrete guidance. Our method, dubbed Make-Your-Video, involves joint-conditional video generation using a Latent Diffusion Model that is pre-trained for still image synthesis and then promoted for video generation with the introduction of temporal modules. This two-stage learning scheme not only reduces the computing resources required, but also improves the performance by transferring the rich concepts available in image datasets solely into video generation. Moreover, we use a simple yet effective causal attention mask strategy to enable longer video synthesis, which mitigates the potential quality degradation effectively. Experimental results show the superiority of our method over existing baselines, particularly in terms of temporal coherence and fidelity to users' guidance. In addition, our model enables several intriguing applications that demonstrate potential for practical usage.

Authors:Eran Levin, Ohad Fried

Abstract: Text-based image editing has advanced significantly in recent years. With the rise of diffusion models, image editing via textual instructions has become ubiquitous. Unfortunately, current models lack the ability to customize the quantity of the change per pixel or per image fragment, resorting to changing the entire image in an equal amount, or editing a specific region using a binary mask. In this paper, we suggest a new framework which enables the user to customize the quantity of change for each image fragment, thereby enhancing the flexibility and verbosity of modern diffusion models. Our framework does not require model training or fine-tuning, but instead performs everything at inference time, making it easily applicable to an existing model. We show both qualitatively and quantitatively that our method allows better controllability and can produce results which are unattainable by existing models. Our code is available at: https://github.com/exx8/differential-diffusion

Authors:Ruohan Gao, Yiming Dou, Hao Li, Tanmay Agarwal, Jeannette Bohg, Yunzhu Li, Li Fei-Fei, Jiajun Wu

Abstract: We introduce the ObjectFolder Benchmark, a benchmark suite of 10 tasks for multisensory object-centric learning, centered around object recognition, reconstruction, and manipulation with sight, sound, and touch. We also introduce the ObjectFolder Real dataset, including the multisensory measurements for 100 real-world household objects, building upon a newly designed pipeline for collecting the 3D meshes, videos, impact sounds, and tactile readings of real-world objects. We conduct systematic benchmarking on both the 1,000 multisensory neural objects from ObjectFolder, and the real multisensory data from ObjectFolder Real. Our results demonstrate the importance of multisensory perception and reveal the respective roles of vision, audio, and touch for different object-centric learning tasks. By publicly releasing our dataset and benchmark suite, we hope to catalyze and enable new research in multisensory object-centric learning in computer vision, robotics, and beyond. Project page: https://objectfolder.stanford.edu

Authors:Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham

Abstract: Text-conditional diffusion models are able to generate high-fidelity images with diverse contents. However, linguistic representations frequently exhibit ambiguous descriptions of the envisioned objective imagery, requiring the incorporation of additional control signals to bolster the efficacy of text-guided diffusion models. In this work, we propose Cocktail, a pipeline to mix various modalities into one embedding, amalgamated with a generalized ControlNet (gControlNet), a controllable normalisation (ControlNorm), and a spatial guidance sampling method, to actualize multi-modal and spatially-refined control for text-conditional diffusion models. Specifically, we introduce a hyper-network gControlNet, dedicated to the alignment and infusion of the control signals from disparate modalities into the pre-trained diffusion model. gControlNet is capable of accepting flexible modality signals, encompassing the simultaneous reception of any combination of modality signals, or the supplementary fusion of multiple modality signals. The control signals are then fused and injected into the backbone model according to our proposed ControlNorm. Furthermore, our advanced spatial guidance sampling methodology proficiently incorporates the control signal into the designated region, thereby circumventing the manifestation of undesired objects within the generated image. We demonstrate the results of our method in controlling various modalities, proving high-quality synthesis and fidelity to multiple external signals.

Authors:Tao Chu, Pan Zhang, Qiong Liu, Jiaqi Wang

Abstract: Understanding and modeling the 3D scene from a single image is a practical problem. A recent advance proposes a panoptic 3D scene reconstruction task that performs both 3D reconstruction and 3D panoptic segmentation from a single image. Although having made substantial progress, recent works only focus on top-down approaches that fill 2D instances into 3D voxels according to estimated depth, which hinders their performance by two ambiguities. (1) instance-channel ambiguity: The variable ids of instances in each scene lead to ambiguity during filling voxel channels with 2D information, confusing the following 3D refinement. (2) voxel-reconstruction ambiguity: 2D-to-3D lifting with estimated single view depth only propagates 2D information onto the surface of 3D regions, leading to ambiguity during the reconstruction of regions behind the frontal view surface. In this paper, we propose BUOL, a Bottom-Up framework with Occupancy-aware Lifting to address the two issues for panoptic 3D scene reconstruction from a single image. For instance-channel ambiguity, a bottom-up framework lifts 2D information to 3D voxels based on deterministic semantic assignments rather than arbitrary instance id assignments. The 3D voxels are then refined and grouped into 3D instances according to the predicted 2D instance centers. For voxel-reconstruction ambiguity, the estimated multi-plane occupancy is leveraged together with depth to fill the whole regions of things and stuff. Our method shows a tremendous performance advantage over state-of-the-art methods on synthetic dataset 3D-Front and real-world dataset Matterport3D. Code and models are available in https://github.com/chtsy/buol.

Authors:Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Mosseri, Lior Wolf

Abstract: Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual concept (e.g., "a doctor", "love"). However, the internal process of mapping text to a rich visual representation remains an enigma. In this work, we tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation. Our code will be available at: https://hila-chefer.github.io/Conceptor/

Authors:Chang Liu, Henghui Ding, Xudong Jiang

Abstract: Referring Expression Segmentation (RES) aims to generate a segmentation mask for the object described by a given language expression. Existing classic RES datasets and methods commonly support single-target expressions only, i.e., one expression refers to one target object. Multi-target and no-target expressions are not considered. This limits the usage of RES in practice. In this paper, we introduce a new benchmark called Generalized Referring Expression Segmentation (GRES), which extends the classic RES to allow expressions to refer to an arbitrary number of target objects. Towards this, we construct the first large-scale GRES dataset called gRefCOCO that contains multi-target, no-target, and single-target expressions. GRES and gRefCOCO are designed to be well-compatible with RES, facilitating extensive experiments to study the performance gap of the existing RES methods on the GRES task. In the experimental study, we find that one of the big challenges of GRES is complex relationship modeling. Based on this, we propose a region-based GRES baseline ReLA that adaptively divides the image into regions with sub-instance clues, and explicitly models the region-region and region-language dependencies. The proposed approach ReLA achieves new state-of-the-art performance on the both newly proposed GRES and classic RES tasks. The proposed gRefCOCO dataset and method are available at https://henghuiding.github.io/GRES.

Authors:Shaozhe Hao, Kai Han, Shihao Zhao, Kwan-Yee K. Wong

Abstract: Personalized text-to-image generation using diffusion models has recently been proposed and attracted lots of attention. Given a handful of images containing a novel concept (e.g., a unique toy), we aim to tune the generative model to capture fine visual details of the novel concept and generate photorealistic images following a text condition. We present a plug-in method, named ViCo, for fast and lightweight personalized generation. Specifically, we propose an image attention module to condition the diffusion process on the patch-wise visual semantics. We introduce an attention-based object mask that comes almost at no cost from the attention module. In addition, we design a simple regularization based on the intrinsic properties of text-image attention maps to alleviate the common overfitting degradation. Unlike many existing models, our method does not finetune any parameters of the original diffusion model. This allows more flexible and transferable model deployment. With only light parameter training (~6% of the diffusion U-Net), our method achieves comparable or even better performance than all state-of-the-art models both qualitatively and quantitatively.

Authors:Chang Liu, Haoning Wu, Yujie Zhong, Xiaoyun Zhang, Weidi Xie

Abstract: Generative models have recently exhibited exceptional capabilities in various scenarios, for example, image generation based on text description. In this work, we focus on the task of generating a series of coherent image sequence based on a given storyline, denoted as open-ended visual storytelling. We make the following three contributions: (i) to fulfill the task of visual storytelling, we introduce two modules into a pre-trained stable diffusion model, and construct an auto-regressive image generator, termed as StoryGen, that enables to generate the current frame by conditioning on both a text prompt and a preceding frame; (ii) to train our proposed model, we collect paired image and text samples by sourcing from various online sources, such as videos, E-books, and establish a data processing pipeline for constructing a diverse dataset, named StorySalon, with a far larger vocabulary than existing animation-specific datasets; (iii) we adopt a three-stage curriculum training strategy, that enables style transfer, visual context conditioning, and human feedback alignment, respectively. Quantitative experiments and human evaluation have validated the superiority of our proposed model, in terms of image quality, style consistency, content consistency, and visual-language alignment. We will make the code, model, and dataset publicly available to the research community.

Authors:Qihao Liu, Adam Kortylewski, Yutong Bai, Song Bai, Alan Yuille

Abstract: Text-guided diffusion models (TDMs) are widely applied but can fail unexpectedly. Common failures include: (i) natural-looking text prompts generating images with the wrong content, or (ii) different random samples of the latent variables that generate vastly different, and even unrelated, outputs despite being conditioned on the same text prompt. In this work, we aim to study and understand the failure modes of TDMs in more detail. To achieve this, we propose SAGE, an adversarial attack on TDMs that uses image classifiers as surrogate loss functions, to search over the discrete prompt space and the high-dimensional latent space of TDMs to automatically discover unexpected behaviors and failure cases in the image generation. We make several technical contributions to ensure that SAGE finds failure cases of the diffusion model, rather than the classifier, and verify this in a human study. Our study reveals four intriguing properties of TDMs that have not been systematically studied before: (1) We find a variety of natural text prompts producing images that fail to capture the semantics of input texts. We categorize these failures into ten distinct types based on the underlying causes. (2) We find samples in the latent space (which are not outliers) that lead to distorted images independent of the text prompt, suggesting that parts of the latent space are not well-structured. (3) We also find latent samples that lead to natural-looking images which are unrelated to the text prompt, implying a potential misalignment between the latent and prompt spaces. (4) By appending a single adversarial token embedding to an input prompt we can generate a variety of specified target objects, while only minimally affecting the CLIP score. This demonstrates the fragility of language representations and raises potential safety concerns.

Authors:Yuanwen Yue, Sabarinath Mahadevan, Jonas Schult, Francis Engelmann, Bastian Leibe, Konrad Schindler, Theodora Kontogianni

Abstract: During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point to an object (or the background), while the user corrects errors in the resulting segmentation and feeds them back into the model. From a machine learning perspective the goal is to design the model and the feedback mechanism in a way that minimizes the required user input. The current best practice segments objects one at a time, and asks the user to provide positive clicks to indicate regions wrongly assigned to the background and negative clicks to indicate regions wrongly assigned to the object (foreground). Sequentially visiting objects is wasteful, since it disregards synergies between objects: a positive click for a given object can, by definition, serve as a negative click for nearby objects, moreover a direct competition between adjacent objects can speed up the identification of their common boundary. We introduce AGILE3D, an efficient, attention-based model that (1) supports simultaneous segmentation of multiple 3D objects, (2) yields more accurate segmentation masks with fewer user clicks, and (3) offers faster inference. We encode the point cloud into a latent feature representation, and view user clicks as queries and employ cross-attention to represent contextual relations between different click locations as well as between clicks and the 3D point cloud features. Every time new clicks are added, we only need to run a lightweight decoder that produces updated segmentation masks. In experiments with four different point cloud datasets, AGILE3D sets a new state of the art, moreover, we also verify its practicality in real-world setups with a real user study.

Authors:Shaowei Liu, Saurabh Gupta, Shenlong Wang

Abstract: We build rearticulable models for arbitrary everyday man-made objects containing an arbitrary number of parts that are connected together in arbitrary ways via 1 degree-of-freedom joints. Given point cloud videos of such everyday objects, our method identifies the distinct object parts, what parts are connected to what other parts, and the properties of the joints connecting each part pair. We do this by jointly optimizing the part segmentation, transformation, and kinematics using a novel energy minimization framework. Our inferred animatable models, enables retargeting to novel poses with sparse point correspondences guidance. We test our method on a new articulating robot dataset, and the Sapiens dataset with common daily objects, as well as real-world scans. Experiments show that our method outperforms two leading prior works on various metrics.

Authors:Yanyu Li, Huan Wang, Qing Jin, Ju Hu, Pavlo Chemerys, Yun Fu, Yanzhi Wang, Sergey Tulyakov, Jian Ren

Abstract: Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models are large, with complex network architectures and tens of denoising iterations, making them computationally expensive and slow to run. As a result, high-end GPUs and cloud-based inference are required to run diffusion models at scale. This is costly and has privacy implications, especially when user data is sent to a third party. To overcome these challenges, we present a generic approach that, for the first time, unlocks running text-to-image diffusion models on mobile devices in less than $2$ seconds. We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation. Further, we enhance the step distillation by exploring training strategies and introducing regularization from classifier-free guidance. Our extensive experiments on MS-COCO show that our model with $8$ denoising steps achieves better FID and CLIP scores than Stable Diffusion v$1.5$ with $50$ steps. Our work democratizes content creation by bringing powerful text-to-image diffusion models to the hands of users.

Authors:Yonglong Tian, Lijie Fan, Phillip Isola, Huiwen Chang, Dilip Krishnan

Abstract: We investigate the potential of learning visual representations using synthetic images generated by text-to-image models. This is a natural question in the light of the excellent performance of such models in generating high-quality images. We consider specifically the Stable Diffusion, one of the leading open source text-to-image models. We show that (1) when the generative model is configured with proper classifier-free guidance scale, training self-supervised methods on synthetic images can match or beat the real image counterpart; (2) by treating the multiple images generated from the same text prompt as positives for each other, we develop a multi-positive contrastive learning method, which we call StableRep. With solely synthetic images, the representations learned by StableRep surpass the performance of representations learned by SimCLR and CLIP using the same set of text prompts and corresponding real images, on large scale datasets. When we further add language supervision, StableRep trained with 20M synthetic images achieves better accuracy than CLIP trained with 50M real images.

Authors:Kihyuk Sohn, Nataniel Ruiz, Kimin Lee, Daniel Castro Chin, Irina Blok, Huiwen Chang, Jarred Barber, Lu Jiang, Glenn Entis, Yuanzhen Li, Yuan Hao, Irfan Essa, Michael Rubinstein, Dilip Krishnan

Abstract: Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts. However, ambiguities inherent in natural language and out-of-distribution effects make it hard to synthesize image styles, that leverage a specific design pattern, texture or material. In this paper, we introduce StyleDrop, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. The proposed method is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. It efficiently learns a new style by fine-tuning very few trainable parameters (less than $1\%$ of total model parameters) and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a single image that specifies the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop implemented on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion. More results are available at our project website: https://styledrop.github.io

Authors:Dave Epstein, Allan Jabri, Ben Poole, Alexei A. Efros, Aleksander Holynski

Abstract: Large-scale generative models are capable of producing high-quality images from detailed text descriptions. However, many aspects of an image are difficult or impossible to convey through text. We introduce self-guidance, a method that provides greater control over generated images by guiding the internal representations of diffusion models. We demonstrate that properties such as the shape, location, and appearance of objects can be extracted from these representations and used to steer sampling. Self-guidance works similarly to classifier guidance, but uses signals present in the pretrained model itself, requiring no additional models or training. We show how a simple set of properties can be composed to perform challenging image manipulations, such as modifying the position or size of objects, merging the appearance of objects in one image with the layout of another, composing objects from many images into one, and more. We also show that self-guidance can be used to edit real images. For results and an interactive demo, see our project page at https://dave.ml/selfguidance/

Authors:Anand Bhattad, Daniel McKee, Derek Hoiem, D. A. Forsyth

Abstract: Intrinsic images, in the original sense, are image-like maps of scene properties like depth, normal, albedo or shading. This paper demonstrates that StyleGAN can easily be induced to produce intrinsic images. The procedure is straightforward. We show that, if StyleGAN produces $G({w})$ from latents ${w}$, then for each type of intrinsic image, there is a fixed offset ${d}_c$ so that $G({w}+{d}_c)$ is that type of intrinsic image for $G({w})$. Here ${d}_c$ is {\em independent of ${w}$}. The StyleGAN we used was pretrained by others, so this property is not some accident of our training regime. We show that there are image transformations StyleGAN will {\em not} produce in this fashion, so StyleGAN is not a generic image regression engine. It is conceptually exciting that an image generator should ``know'' and represent intrinsic images. There may also be practical advantages to using a generative model to produce intrinsic images. The intrinsic images obtained from StyleGAN compare well both qualitatively and quantitatively with those obtained by using SOTA image regression techniques; but StyleGAN's intrinsic images are robust to relighting effects, unlike SOTA methods.

Authors:Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li, Christoph Feichtenhofer

Abstract: Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to effective accuracies and attractive FLOP counts, the added complexity actually makes these transformers slower than their vanilla ViT counterparts. In this paper, we argue that this additional bulk is unnecessary. By pretraining with a strong visual pretext task (MAE), we can strip out all the bells-and-whistles from a state-of-the-art multi-stage vision transformer without losing accuracy. In the process, we create Hiera, an extremely simple hierarchical vision transformer that is more accurate than previous models while being significantly faster both at inference and during training. We evaluate Hiera on a variety of tasks for image and video recognition. Our code and models are available at https://github.com/facebookresearch/hiera.

Authors:Jiahui Huang, Zan Gojcic, Matan Atzmon, Or Litany, Sanja Fidler, Francis Williams

Abstract: We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural Kernel Fields (NKF) representation. It enjoys similar generalization capabilities to NKF, while simultaneously addressing its main limitations: (a) We can scale to large scenes through compactly supported kernel functions, which enable the use of memory-efficient sparse linear solvers. (b) We are robust to noise, through a gradient fitting solve. (c) We minimize training requirements, enabling us to learn from any dataset of dense oriented points, and even mix training data consisting of objects and scenes at different scales. Our method is capable of reconstructing millions of points in a few seconds, and handling very large scenes in an out-of-core fashion. We achieve state-of-the-art results on reconstruction benchmarks consisting of single objects, indoor scenes, and outdoor scenes.

Authors:Sivan Doveh, Assaf Arbelle, Sivan Harary, Amit Alfassy, Roei Herzig, Donghyun Kim, Raja Giryes, Rogerio Feris, Rameswar Panda, Shimon Ullman, Leonid Karlinsky

Abstract: Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the aligned image-text spaces learned by all the popular VL models are still suffering from the so-called `object bias' - their representations behave as `bags of nouns', mostly ignoring or downsizing the attributes, relations, and states of objects described/appearing in texts/images. Although some great attempts at fixing these `compositional reasoning' issues were proposed in the recent literature, the problem is still far from being solved. In this paper, we uncover two factors limiting the VL models' compositional reasoning performance. These two factors are properties of the paired VL dataset used for finetuning and pre-training the VL model: (i) the caption quality, or in other words `image-alignment', of the texts; and (ii) the `density' of the captions in the sense of mentioning all the details appearing on the image. We propose a fine-tuning approach for automatically treating these factors leveraging a standard VL dataset (CC3M). Applied to CLIP, we demonstrate its significant compositional reasoning performance increase of up to $\sim27\%$ over the base model, up to $\sim20\%$ over the strongest baseline, and by $6.7\%$ on average.

Authors:Guian Fang, Zutao Jiang, Jianhua Han, Guangsong Lu, Hang Xu, Xiaodan Liang

Abstract: Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from given text prompts. However, previous methods fail to perform accurate modality alignment between text concepts and generated images due to the lack of fine-level semantic guidance that successfully diagnoses the modality discrepancy. In this paper, we propose FineRewards to improve the alignment between text and images in text-to-image diffusion models by introducing two new fine-grained semantic rewards: the caption reward and the Semantic Segment Anything (SAM) reward. From the global semantic view, the caption reward generates a corresponding detailed caption that depicts all important contents in the synthetic image via a BLIP-2 model and then calculates the reward score by measuring the similarity between the generated caption and the given prompt. From the local semantic view, the SAM reward segments the generated images into local parts with category labels, and scores the segmented parts by measuring the likelihood of each category appearing in the prompted scene via a large language model, i.e., Vicuna-7B. Additionally, we adopt an assemble reward-ranked learning strategy to enable the integration of multiple reward functions to jointly guide the model training. Adapting results of text-to-image models on the MS-COCO benchmark show that the proposed semantic reward outperforms other baseline reward functions with a considerable margin on both visual quality and semantic similarity with the input prompt. Moreover, by adopting the assemble reward-ranked learning strategy, we further demonstrate that model performance is further improved when adapting under the unifying of the proposed semantic reward with the current image rewards.

Authors:Guofan Fan, Zekun Qi, Wenkai Shi, Kaisheng Ma

Abstract: Geometry and color information provided by the point clouds are both crucial for 3D scene understanding. Two pieces of information characterize the different aspects of point clouds, but existing methods lack an elaborate design for the discrimination and relevance. Hence we explore a 3D self-supervised paradigm that can better utilize the relations of point cloud information. Specifically, we propose a universal 3D scene pre-training framework via Geometry-Color Contrast (Point-GCC), which aligns geometry and color information using a Siamese network. To take care of actual application tasks, we design (i) hierarchical supervision with point-level contrast and reconstruct and object-level contrast based on the novel deep clustering module to close the gap between pre-training and downstream tasks; (ii) architecture-agnostic backbone to adapt for various downstream models. Benefiting from the object-level representation associated with downstream tasks, Point-GCC can directly evaluate model performance and the result demonstrates the effectiveness of our methods. Transfer learning results on a wide range of tasks also show consistent improvements across all datasets. e.g., new state-of-the-art object detection results on SUN RGB-D and S3DIS datasets. Codes will be released at https://github.com/Asterisci/Point-GCC.

Authors:Matthew Korban, Scott T. Acton, Peter Youngs

Abstract: This paper proposes a novel multi-modal transformer network for detecting actions in untrimmed videos. To enrich the action features, our transformer network utilizes a new multi-modal attention mechanism that computes the correlations between different spatial and motion modalities combinations. Exploring such correlations for actions has not been attempted previously. To use the motion and spatial modality more effectively, we suggest an algorithm that corrects the motion distortion caused by camera movement. Such motion distortion, common in untrimmed videos, severely reduces the expressive power of motion features such as optical flow fields. Our proposed algorithm outperforms the state-of-the-art methods on two public benchmarks, THUMOS14 and ActivityNet. We also conducted comparative experiments on our new instructional activity dataset, including a large set of challenging classroom videos captured from elementary schools.

Authors:Cosmin I. Bercea, Michael Neumayr, Daniel Rueckert, Julia A. Schnabel

Abstract: The introduction of diffusion models in anomaly detection has paved the way for more effective and accurate image reconstruction in pathologies. However, the current limitations in controlling noise granularity hinder diffusion models' ability to generalize across diverse anomaly types and compromise the restoration of healthy tissues. To overcome these challenges, we propose AutoDDPM, a novel approach that enhances the robustness of diffusion models. AutoDDPM utilizes diffusion models to generate initial likelihood maps of potential anomalies and seamlessly integrates them with the original image. Through joint noised distribution re-sampling, AutoDDPM achieves harmonization and in-painting effects. Our study demonstrates the efficacy of AutoDDPM in replacing anomalous regions while preserving healthy tissues, considerably surpassing diffusion models' limitations. It also contributes valuable insights and analysis on the limitations of current diffusion models, promoting robust and interpretable anomaly detection in medical imaging - an essential aspect of building autonomous clinical decision systems with higher interpretability.

Authors:Ali Vosoughi, Shijian Deng, Songyang Zhang, Yapeng Tian, Chenliang Xu, Jiebo Luo

Abstract: To increase the generalization capability of VQA systems, many recent studies have tried to de-bias spurious language or vision associations that shortcut the question or image to the answer. Despite these efforts, the literature fails to address the confounding effect of vision and language simultaneously. As a result, when they reduce bias learned from one modality, they usually increase bias from the other. In this paper, we first model a confounding effect that causes language and vision bias simultaneously, then propose a counterfactual inference to remove the influence of this effect. The model trained in this strategy can concurrently and efficiently reduce vision and language bias. To the best of our knowledge, this is the first work to reduce biases resulting from confounding effects of vision and language in VQA, leveraging causal explain-away relations. We accompany our method with an explain-away strategy, pushing the accuracy of the questions with numerical answers results compared to existing methods that have been an open problem. The proposed method outperforms the state-of-the-art methods in VQA-CP v2 datasets.

Authors:Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios, Osman Semih Kayhan, Davide Zambrano, Nergis Tomen, Jan van Gemert

Abstract: The third edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop featured four data-impaired challenges, focusing on addressing the limitations of data availability in training deep learning models for computer vision tasks. The challenges comprised of four distinct data-impaired tasks, where participants were required to train models from scratch using a reduced number of training samples. The primary objective was to encourage novel approaches that incorporate relevant inductive biases to enhance the data efficiency of deep learning models. To foster creativity and exploration, participants were strictly prohibited from utilizing pre-trained checkpoints and other transfer learning techniques. Significant advancements were made compared to the provided baselines, where winning solutions surpassed the baselines by a considerable margin in all four tasks. These achievements were primarily attributed to the effective utilization of extensive data augmentation policies, model ensembling techniques, and the implementation of data-efficient training methods, including self-supervised representation learning. This report highlights the key aspects of the challenges and their outcomes.

Authors:Haijun Xiong, Yunze Deng, Xiaohu Huang, Xinggang Wang, Wenyu Liu, Bin Feng

Abstract: Gait recognition is an emerging biological recognition technology that identifies and verifies individuals based on their walking patterns. However, many current methods are limited in their use of temporal information. In order to fully harness the potential of gait recognition, it is crucial to consider temporal features at various granularities and spans. Hence, in this paper, we propose a novel framework named GaitGS, which aggregates temporal features in the granularity dimension and span dimension simultaneously. Specifically, Multi-Granularity Feature Extractor (MGFE) is proposed to focus on capturing the micro-motion and macro-motion information at the frame level and unit level respectively. Moreover, we present Multi-Span Feature Learning (MSFL) module to generate global and local temporal representations. On three popular gait datasets, extensive experiments demonstrate the state-of-the-art performance of our method. Our method achieves the Rank-1 accuracies of 92.9% (+0.5%), 52.0% (+1.4%), and 97.5% (+0.8%) on CASIA-B, GREW, and OU-MVLP respectively. The source code will be released soon.

Authors:Yufei Guo, Xuhui Huang, Zhe Ma

Abstract: The spiking neural network (SNN), as a promising brain-inspired computational model with binary spike information transmission mechanism, rich spatially-temporal dynamics, and event-driven characteristics, has received extensive attention. However, its intricately discontinuous spike mechanism brings difficulty to the optimization of the deep SNN. Since the surrogate gradient method can greatly mitigate the optimization difficulty and shows great potential in directly training deep SNNs, a variety of direct learning-based deep SNN works have been proposed and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these direct learning-based deep SNN works, mainly categorized into accuracy improvement methods, efficiency improvement methods, and temporal dynamics utilization methods. In addition, we also divide these categorizations into finer granularities further to better organize and introduce them. Finally, the challenges and trends that may be faced in future research are prospected.

Authors:Antonin Sulc, Imari Sato, Bastian Goldluecke, Tali Treibitz

Abstract: Refraction is a common physical phenomenon and has long been researched in computer vision. Objects imaged through a refractive object appear distorted in the image as a function of the shape of the interface between the media. This hinders many computer vision applications, but can be utilized for obtaining the geometry of the refractive interface. Previous approaches for refractive surface recovery largely relied on various priors or additional information like multiple images of the analyzed surface. In contrast, we claim that a simple energy function based on Snell's law enables the reconstruction of an arbitrary refractive surface geometry using just a single image and known background texture and geometry. In the case of a single point, Snell's law has two degrees of freedom, therefore to estimate a surface depth, we need additional information. We show that solving for an entire surface at once introduces implicit parameter-free spatial regularization and yields convincing results when an intelligent initial guess is provided. We demonstrate our approach through simulations and real-world experiments, where the reconstruction shows encouraging results in the single-frame monocular setting.

Authors:Zhisheng Wang, Yue Liu, Shunli Wang, Xingyuan Bian, Zongfeng Li, Junning Cui

Abstract: This paper is to investigate the high-quality analytical reconstructions of multiple source-translation computed tomography (mSTCT) under an extended field of view (FOV). Under the larger FOVs, the previously proposed backprojection filtration (BPF) algorithms for mSTCT, including D-BPF and S-BPF, make some intolerable errors in the image edges due to an unstable backprojection weighting factor and the half-scan mode, which deviates from the intention of mSTCT imaging. In this paper, to achieve reconstruction with as little error as possible under the extremely extended FOV, we propose two strategies, including deriving a no-weighting D-BPF (NWD-BPF) for mSTCT and introducing BPFs into a special full-scan mSTCT (F-mSTCT) to balance errors, i.e., abbreviated as FD-BPF and FS-BPF. For the first strategy, we eliminate this unstable backprojection weighting factor by introducing a special variable relationship in D-BPF. For the second strategy, we combine the F-mSTCT geometry with BPFs to study the performance and derive a suitable redundant weighting function for F-mSTCT. The experiments demonstrate our proposed methods for these strategies. Among them, NWD-BPF can weaken the instability at the image edges but blur the details, and FS-BPF can get high-quality stable images under the extremely extended FOV imaging a large object but requires more projections than FD-BPF. For different practical requirements in extending FOV imaging, we give suggestions on algorithm selection.

Authors:Davide Evangelista, Elena Morotti, Elena Loli Piccolomini, James Nagy

Abstract: In recent years, large convolutional neural networks have been widely used as tools for image deblurring, because of their ability in restoring images very precisely. It is well known that image deblurring is mathematically modeled as an ill-posed inverse problem and its solution is difficult to approximate when noise affects the data. Really, one limitation of neural networks for deblurring is their sensitivity to noise and other perturbations, which can lead to instability and produce poor reconstructions. In addition, networks do not necessarily take into account the numerical formulation of the underlying imaging problem, when trained end-to-end. In this paper, we propose some strategies to improve stability without losing to much accuracy to deblur images with deep-learning based methods. First, we suggest a very small neural architecture, which reduces the execution time for training, satisfying a green AI need, and does not extremely amplify noise in the computed image. Second, we introduce a unified framework where a pre-processing step balances the lack of stability of the following, neural network-based, step. Two different pre-processors are presented: the former implements a strong parameter-free denoiser, and the latter is a variational model-based regularized formulation of the latent imaging problem. This framework is also formally characterized by mathematical analysis. Numerical experiments are performed to verify the accuracy and stability of the proposed approaches for image deblurring when unknown or not-quantified noise is present; the results confirm that they improve the network stability with respect to noise. In particular, the model-based framework represents the most reliable trade-off between visual precision and robustness.

Authors:Michaël Fonder, Marc Van Droogenbroeck

Abstract: When used by autonomous vehicles for trajectory planning or obstacle avoidance, depth estimation methods need to be reliable. Therefore, estimating the quality of the depth outputs is critical. In this paper, we show how M4Depth, a state-of-the-art depth estimation method designed for unmanned aerial vehicle (UAV) applications, can be enhanced to perform joint depth and uncertainty estimation. For that, we present a solution to convert the uncertainty estimates related to parallax generated by M4Depth into uncertainty estimates related to depth, and show that it outperforms the standard probabilistic approach. Our experiments on various public datasets demonstrate that our method performs consistently, even in zero-shot transfer. Besides, our method offers a compelling value when compared to existing multi-view depth estimation methods as it performs similarly on a multi-view depth estimation benchmark despite being 2.5 times faster and causal, as opposed to other methods. The code of our method is publicly available at https://github.com/michael-fonder/M4DepthU .

Authors:Xianwei Lv, Claudio Persello, Xiao Huang, Dongping Ming, Alfred Stein

Abstract: Accurate segmentation of large areas from very high spatial-resolution (VHR) remote sensing imagery remains a challenging issue in image analysis. Existing supervised and unsupervised methods both suffer from the large variance of object sizes and the difficulty in scale selection, which often result in poor segmentation accuracies. To address the above challenges, we propose a deep learning-based region-merging method (DeepMerge) to handle the segmentation in large VHR images by integrating a Transformer with a multi-level embedding module, a segment-based feature embedding module and a region-adjacency graph model. In addition, we propose a modified binary tree sampling method to generate multi-level inputs from initial segmentation results, serving as inputs for the DeepMerge model. To our best knowledge, the proposed method is the first to use deep learning to learn the similarity between adjacent segments for region-merging. The proposed DeepMerge method is validated using a remote sensing image of 0.55m resolution covering an area of 5,660 km^2 acquired from Google Earth. The experimental results show that the proposed DeepMerge with the highest F value (0.9446) and the lowest TE (0.0962) and ED2 (0.8989) is able to correctly segment objects of different sizes and outperforms all selected competing segmentation methods from both quantitative and qualitative assessments.

Authors:Hyungjin Chung, Jeongsol Kim, Jong Chul Ye

Abstract: Diffusion model-based inverse problem solvers have shown impressive performance, but are limited in speed, mostly as they require reverse diffusion sampling starting from noise. Several recent works have tried to alleviate this problem by building a diffusion process, directly bridging the clean and the corrupted for specific inverse problems. In this paper, we first unify these existing works under the name Direct Diffusion Bridges (DDB), showing that while motivated by different theories, the resulting algorithms only differ in the choice of parameters. Then, we highlight a critical limitation of the current DDB framework, namely that it does not ensure data consistency. To address this problem, we propose a modified inference procedure that imposes data consistency without the need for fine-tuning. We term the resulting method data Consistent DDB (CDDB), which outperforms its inconsistent counterpart in terms of both perception and distortion metrics, thereby effectively pushing the Pareto-frontier toward the optimum. Our proposed method achieves state-of-the-art results on both evaluation criteria, showcasing its superiority over existing methods.

Authors:Aoran Xiao, Xiaoqin Zhang, Ling Shao, Shijian Lu

Abstract: In the past decade, deep neural networks have achieved significant progress in point cloud learning. However, collecting large-scale precisely-annotated training data is extremely laborious and expensive, which hinders the scalability of existing point cloud datasets and poses a bottleneck for efficient exploration of point cloud data in various tasks and applications. Label-efficient learning offers a promising solution by enabling effective deep network training with much-reduced annotation efforts. This paper presents the first comprehensive survey of label-efficient learning of point clouds. We address three critical questions in this emerging research field: i) the importance and urgency of label-efficient learning in point cloud processing, ii) the subfields it encompasses, and iii) the progress achieved in this area. To achieve this, we propose a taxonomy that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels. We categorize four typical label-efficient learning approaches that significantly reduce point cloud annotation efforts: data augmentation, domain transfer learning, weakly-supervised learning, and pretrained foundation models. For each approach, we outline the problem setup and provide an extensive literature review that showcases relevant progress and challenges. Finally, we share insights into current research challenges and potential future directions. A project associated with this survey has been built at \url{https://github.com/xiaoaoran/3D_label_efficient_learning}.

Authors:Yi Sun, Xin Xu, Jian Li, Xiaochang Hu, Yifei Shi, Ling-Li Zeng

Abstract: Multi-output deep neural networks(MONs) contain multiple task branches, and these tasks usually share partial network filters that lead to the entanglement of different task inference routes. Due to the inconsistent optimization objectives, the task gradients used for training MONs will interfere with each other on the shared routes, which will decrease the overall model performance. To address this issue, we propose a novel gradient de-conflict algorithm named DR-MGF(Dynamic Routes and Meta-weighted Gradient Fusion) in this work. Different from existing de-conflict methods, DR-MGF achieves gradient de-conflict in MONs by learning task-preferred inference routes. The proposed method is motivated by our experimental findings: the shared filters are not equally important to different tasks. By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks. Through making the dominances of tasks over filters be proportional to the task-specific importance of filters, DR-MGF can effectively reduce the inter-task interference. The task-specific importance variables ultimately determine task-preferred inference routes at the end of training iterations. Extensive experimental results on CIFAR, ImageNet, and NYUv2 illustrate that DR-MGF outperforms the existing de-conflict methods both in prediction accuracy and convergence speed of MONs. Furthermore, DR-MGF can be extended to general MONs without modifying the overall network structures.

Authors:Uğur Çoğalan, Mojtaba Bemana, Hans-Peter Seidel, Karol Myszkowski

Abstract: Full-reference image quality metrics (FR-IQMs) aim to measure the visual differences between a pair of reference and distorted images, with the goal of accurately predicting human judgments. However, existing FR-IQMs, including traditional ones like PSNR and SSIM and even perceptual ones such as HDR-VDP, LPIPS, and DISTS, still fall short in capturing the complexities and nuances of human perception. In this work, rather than devising a novel IQM model, we seek to improve upon the perceptual quality of existing FR-IQM methods. We achieve this by considering visual masking, an important characteristic of the human visual system that changes its sensitivity to distortions as a function of local image content. Specifically, for a given FR-IQM metric, we propose to predict a visual masking model that modulates reference and distorted images in a way that penalizes the visual errors based on their visibility. Since the ground truth visual masks are difficult to obtain, we demonstrate how they can be derived in a self-supervised manner solely based on mean opinion scores (MOS) collected from an FR-IQM dataset. Our approach results in enhanced FR-IQM metrics that are more in line with human prediction both visually and quantitatively.

Authors:Wei Shang, Dongwei Ren, Chaoyu Feng, Xiaotao Wang, Lei Lei, Wangmeng Zuo

Abstract: Modern consumer cameras usually employ the rolling shutter (RS) mechanism, where images are captured by scanning scenes row-by-row, yielding RS distortions for dynamic scenes. To correct RS distortions, existing methods adopt a fully supervised learning manner, where high framerate global shutter (GS) images should be collected as ground-truth supervision. In this paper, we propose a Self-supervised learning framework for Dual reversed RS distortions Correction (SelfDRSC), where a DRSC network can be learned to generate a high framerate GS video only based on dual RS images with reversed distortions. In particular, a bidirectional distortion warping module is proposed for reconstructing dual reversed RS images, and then a self-supervised loss can be deployed to train DRSC network by enhancing the cycle consistency between input and reconstructed dual reversed RS images. Besides start and end RS scanning time, GS images at arbitrary intermediate scanning time can also be supervised in SelfDRSC, thus enabling the learned DRSC network to generate a high framerate GS video. Moreover, a simple yet effective self-distillation strategy is introduced in self-supervised loss for mitigating boundary artifacts in generated GS images. On synthetic dataset, SelfDRSC achieves better or comparable quantitative metrics in comparison to state-of-the-art methods trained in the full supervision manner. On real-world RS cases, our SelfDRSC can produce high framerate GS videos with finer correction textures and better temporary consistency. The source code and trained models are made publicly available at https://github.com/shangwei5/SelfDRSC.

Authors:Subhankar Roy, Riccardo Volpi, Gabriela Csurka, Diane Larlus

Abstract: Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories. This is typically carried out by providing expensive pixel-level annotations to the training algorithm for all new objects, limiting the adoption of such methods in practical applications. Approaches that solely require image-level labels offer an attractive alternative, yet, such coarse annotations lack precise information about the location and boundary of the new objects. In this paper we argue that, since classes represent not just indices but semantic entities, the conceptual relationships between them can provide valuable information that should be leveraged. We propose a weakly supervised approach that exploits such semantic relations to transfer objectness prior from the previously learned classes into the new ones, complementing the supervisory signal from image-level labels. We validate our approach on a number of continual learning tasks, and show how even a simple pairwise interaction between classes can significantly improve the segmentation mask quality of both old and new classes. We show these conclusions still hold for longer and, hence, more realistic sequences of tasks and for a challenging few-shot scenario.

Authors:Chen Yang, Kailing Wang, Yuehao Wang, Xiaokang Yang, Wei Shen

Abstract: Reconstructing deformable tissues from endoscopic stereo videos in robotic surgery is crucial for various clinical applications. However, existing methods relying only on implicit representations are computationally expensive and require dozens of hours, which limits further practical applications. To address this challenge, we introduce LerPlane, a novel method for fast and accurate reconstruction of surgical scenes under a single-viewpoint setting. LerPlane treats surgical procedures as 4D volumes and factorizes them into explicit 2D planes of static and dynamic fields, leading to a compact memory footprint and significantly accelerated optimization. The efficient factorization is accomplished by fusing features obtained through linear interpolation of each plane and enables using lightweight neural networks to model surgical scenes. Besides, LerPlane shares static fields, significantly reducing the workload of dynamic tissue modeling. We also propose a novel sample scheme to boost optimization and improve performance in regions with tool occlusion and large motions. Experiments on DaVinci robotic surgery videos demonstrate that LerPlane accelerates optimization by over 100$\times$ while maintaining high quality across various non-rigid deformations, showing significant promise for future intraoperative surgery applications.

Authors:Yi Gu, Yoshito Otake, Keisuke Uemura, Masaki Takao, Mazen Soufi, Yuta Hiasa, Hugues Talbot, Seiji Okata, Nobuhiko Sugano, Yoshinobu Sato

Abstract: Musculoskeletal diseases such as sarcopenia and osteoporosis are major obstacles to health during aging. Although dual-energy X-ray absorptiometry (DXA) and computed tomography (CT) can be used to evaluate musculoskeletal conditions, frequent monitoring is difficult due to the cost and accessibility (as well as high radiation exposure in the case of CT). We propose a method (named MSKdeX) to estimate fine-grained muscle properties from a plain X-ray image, a low-cost, low-radiation, and highly accessible imaging modality, through musculoskeletal decomposition leveraging fine-grained segmentation in CT. We train a multi-channel quantitative image translation model to decompose an X-ray image into projections of CT of individual muscles to infer the lean muscle mass and muscle volume. We propose the object-wise intensity-sum loss, a simple yet surprisingly effective metric invariant to muscle deformation and projection direction, utilizing information in CT and X-ray images collected from the same patient. While our method is basically an unpaired image-to-image translation, we also exploit the nature of the bone's rigidity, which provides the paired data through 2D-3D rigid registration, adding strong pixel-wise supervision in unpaired training. Through the evaluation using a 539-patient dataset, we showed that the proposed method significantly outperformed conventional methods. The average Pearson correlation coefficient between the predicted and CT-derived ground truth metrics was increased from 0.460 to 0.863. We believe our method opened up a new musculoskeletal diagnosis method and has the potential to be extended to broader applications in multi-channel quantitative image translation tasks. Our source code will be released soon.

Authors:AJ Piergiovanni, Anelia Angelova

Abstract: Image-language learning has made unprecedented progress in visual understanding. These developments have come at high costs, as contemporary vision-language models require large model scales and amounts of data. We here propose a much easier recipe for image-language learning, which produces effective models, outperforming bigger and more expensive ones, often trained on orders of magnitude larger datasets. Our key finding is the joint learning of a compact vision and language representation, which adaptively and iteratively fuses the multi-modal features. This results in a more effective image-language learning, greatly lowering the FLOPs by combining and reducing the number of tokens for both text and images, e.g. a 33\% reduction in FLOPs is achieved, compared to baseline fusion techniques used by popular image-language models, while improving performance. This also allows the model to scale without a large increase in FLOPs or memory. In addition, we propose adaptive pre-training data sampling which improves the data efficiency. The proposed approach achieves competitive performance compared to much larger models, and does so with significantly less data and FLOPs. With only 40M training examples and with 39 GFLOPs our lightweight model outperforms many times larger state-of-the-art models of 2-20x more FLOPs and using bigger datasets some of which with close to 1B training examples.

Authors:Brennon Maistry, Absalom E. Ezugwu

Abstract: Breast cancer is a prevalent form of cancer among women, with over 1.5 million women being diagnosed each year. Unfortunately, the survival rates for breast cancer patients in certain third-world countries, like South Africa, are alarmingly low, with only 40% of diagnosed patients surviving beyond five years. The inadequate availability of resources, including qualified pathologists, delayed diagnoses, and ineffective therapy planning, contribute to this low survival rate. To address this pressing issue, medical specialists and researchers have turned to domain-specific AI approaches, specifically deep learning models, to develop end-to-end solutions that can be integrated into computer-aided diagnosis (CAD) systems. By improving the workflow of pathologists, these AI models have the potential to enhance the detection and diagnosis of breast cancer. This research focuses on evaluating the performance of various cutting-edge convolutional neural network (CNN) architectures in comparison to a relatively new model called the Vision Trans-former (ViT). The objective is to determine the superiority of these models in terms of their accuracy and effectiveness. The experimental results reveal that the ViT models outperform the other selected state-of-the-art CNN architectures, achieving an impressive accuracy rate of 95.15%. This study signifies a significant advancement in the field, as it explores the utilization of data augmentation and other relevant preprocessing techniques in conjunction with deep learning models for the detection and diagnosis of breast cancer using datasets of Breast Cancer Histopathological Image Classification.

Authors:Muhammad Imran, Brianna Nguyen, Jake Pensa, Sara M. Falzarano, Anthony E. Sisk, Muxua Liang, John Michael DiBianco, Li-Ming Su, Yuyin Zhou, Wayne G. Brisbane, Wei Shao

Abstract: Early diagnosis of prostate cancer significantly improves a patient's 5-year survival rate. Biopsy of small prostate cancers is improved with image-guided biopsy. MRI-ultrasound fusion-guided biopsy is sensitive to smaller tumors but is underutilized due to the high cost of MRI and fusion equipment. Micro-ultrasound (micro-US), a novel high-resolution ultrasound technology, provides a cost-effective alternative to MRI while delivering comparable diagnostic accuracy. However, the interpretation of micro-US is challenging due to subtle gray scale changes indicating cancer vs normal tissue. This challenge can be addressed by training urologists with a large dataset of micro-US images containing the ground truth cancer outlines. Such a dataset can be mapped from surgical specimens (histopathology) onto micro-US images via image registration. In this paper, we present a semi-automated pipeline for registering in vivo micro-US images with ex vivo whole-mount histopathology images. Our pipeline begins with the reconstruction of pseudo-whole-mount histopathology images and a 3D micro-US volume. Each pseudo-whole-mount histopathology image is then registered with the corresponding axial micro-US slice using a two-stage approach that estimates an affine transformation followed by a deformable transformation. We evaluated our registration pipeline using micro-US and histopathology images from 18 patients who underwent radical prostatectomy. The results showed a Dice coefficient of 0.94 and a landmark error of 2.7 mm, indicating the accuracy of our registration pipeline. This proof-of-concept study demonstrates the feasibility of accurately aligning micro-US and histopathology images. To promote transparency and collaboration in research, we will make our code and dataset publicly available.

Authors:Defang Chen, Zhenyu Zhou, Jian-Ping Mei, Chunhua Shen, Chun Chen, Can Wang

Abstract: Recent years have witnessed significant progress in developing efficient training and fast sampling approaches for diffusion models. A recent remarkable advancement is the use of stochastic differential equations (SDEs) to describe data perturbation and generative modeling in a unified mathematical framework. In this paper, we reveal several intriguing geometric structures of diffusion models and contribute a simple yet powerful interpretation to their sampling dynamics. Through carefully inspecting a popular variance-exploding SDE and its marginal-preserving ordinary differential equation (ODE) for sampling, we discover that the data distribution and the noise distribution are smoothly connected with an explicit, quasi-linear sampling trajectory, and another implicit denoising trajectory, which even converges faster in terms of visual quality. We also establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm, with which we can characterize the asymptotic behavior of diffusion models and identify the score deviation. These new geometric observations enable us to improve previous sampling algorithms, re-examine latent interpolation, as well as re-explain the working principles of distillation-based fast sampling techniques.

Authors:Ziyang Chen, Yongsheng Pan, Yiwen Ye, Hengfei Cui, Yong Xia

Abstract: Although recent years have witnessed the great success of convolutional neural networks (CNNs) in medical image segmentation, the domain shift issue caused by the highly variable image quality of medical images hinders the deployment of CNNs in real-world clinical applications. Domain generalization (DG) methods aim to address this issue by training a robust model on the source domain, which has a strong generalization ability. Previously, many DG methods based on feature-space domain randomization have been proposed, which, however, suffer from the limited and unordered search space of feature styles. In this paper, we propose a multi-source DG method called Treasure in Distribution (TriD), which constructs an unprecedented search space to obtain the model with strong robustness by randomly sampling from a uniform distribution. To learn the domain-invariant representations explicitly, we further devise a style-mixing strategy in our TriD, which mixes the feature styles by randomly mixing the augmented and original statistics along the channel wise and can be extended to other DG methods. Extensive experiments on two medical segmentation tasks with different modalities demonstrate that our TriD achieves superior generalization performance on unseen target-domain data. Code is available at https://github.com/Chen-Ziyang/TriD.

Authors:Hongxu Jiang, Muhammad Imran, Preethika Muralidharan, Anjali Patel, Jake Pensa, Muxuan Liang, Tarik Benidir, Joseph R. Grajo, Jason P. Joseph, Russell Terry, John Michael DiBianco, Li-Ming Su, Yuyin Zhou, Wayne G. Brisbane, Wei Shao

Abstract: Micro-ultrasound (micro-US) is a novel 29-MHz ultrasound technique that provides 3-4 times higher resolution than traditional ultrasound, delivering comparable accuracy for diagnosing prostate cancer to MRI but at a lower cost. Accurate prostate segmentation is crucial for prostate volume measurement, cancer diagnosis, prostate biopsy, and treatment planning. This paper proposes a deep learning approach for automated, fast, and accurate prostate segmentation on micro-US images. Prostate segmentation on micro-US is challenging due to artifacts and indistinct borders between the prostate, bladder, and urethra in the midline. We introduce MicroSegNet, a multi-scale annotation-guided Transformer UNet model to address this challenge. During the training process, MicroSegNet focuses more on regions that are hard to segment (challenging regions), where expert and non-expert annotations show discrepancies. We achieve this by proposing an annotation-guided cross entropy loss that assigns larger weight to pixels in hard regions and lower weight to pixels in easy regions. We trained our model using micro-US images from 55 patients, followed by evaluation on 20 patients. Our MicroSegNet model achieved a Dice coefficient of 0.942 and a Hausdorff distance of 2.11 mm, outperforming several state-of-the-art segmentation methods, as well as three human annotators with different experience levels. We will make our code and dataset publicly available to promote transparency and collaboration in research.

Authors:Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Tongliang Liu, Bo Du, Dacheng Tao

Abstract: End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection and recognition simultaneously and efficiently. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, DeepSolo not only performs well in English scenes but also masters the Chinese transcription with complex font structure and a thousand-level character classes. On the other hand, based on the extensibility of DeepSolo, we launch DeepSolo++ for multilingual text spotting, making a further step to let Transformer decoder with explicit points solo for multilingual text detection, recognition, and script identification all at once. Extensive experiments on public benchmarks demonstrate that our simple approach achieves better training efficiency compared with Transformer-based models and outperforms the previous state-of-the-art. In addition, DeepSolo and DeepSolo++ are also compatible with line annotations, which require much less annotation cost than polygons. The code is available at \url{https://github.com/ViTAE-Transformer/DeepSolo}.

Authors:Pietro Melzi, Christian Rathgeb, Ruben Tolosana, Ruben Vera-Rodriguez, Dominik Lawatsch, Florian Domin, Maxim Schaubert

Abstract: Face recognition systems have significantly advanced in recent years, driven by the availability of large-scale datasets. However, several issues have recently came up, including privacy concerns that have led to the discontinuation of well-established public datasets. Synthetic datasets have emerged as a solution, even though current synthesis methods present other drawbacks such as limited intra-class variations, lack of realism, and unfair representation of demographic groups. This study introduces GANDiffFace, a novel framework for the generation of synthetic datasets for face recognition that combines the power of Generative Adversarial Networks (GANs) and Diffusion models to overcome the limitations of existing synthetic datasets. In GANDiffFace, we first propose the use of GANs to synthesize highly realistic identities and meet target demographic distributions. Subsequently, we fine-tune Diffusion models with the images generated with GANs, synthesizing multiple images of the same identity with a variety of accessories, poses, expressions, and contexts. We generate multiple synthetic datasets by changing GANDiffFace settings, and compare their mated and non-mated score distributions with the distributions provided by popular real-world datasets for face recognition, i.e. VGG2 and IJB-C. Our results show the feasibility of the proposed GANDiffFace, in particular the use of Diffusion models to enhance the (limited) intra-class variations provided by GANs towards the level of real-world datasets.

Authors:Xiaoyuan Guo, Kezhen Chen, Jinmeng Rao, Yawen Zhang, Baochen Sun, Jie Yang

Abstract: We present LOWA, a novel method for localizing objects with attributes effectively in the wild. It aims to address the insufficiency of current open-vocabulary object detectors, which are limited by the lack of instance-level attribute classification and rare class names. To train LOWA, we propose a hybrid vision-language training strategy to learn object detection and recognition with class names as well as attribute information. With LOWA, users can not only detect objects with class names, but also able to localize objects by attributes. LOWA is built on top of a two-tower vision-language architecture and consists of a standard vision transformer as the image encoder and a similar transformer as the text encoder. To learn the alignment between visual and text inputs at the instance level, we train LOWA with three training steps: object-level training, attribute-aware learning, and free-text joint training of objects and attributes. This hybrid training strategy first ensures correct object detection, then incorporates instance-level attribute information, and finally balances the object class and attribute sensitivity. We evaluate our model performance of attribute classification and attribute localization on the Open-Vocabulary Attribute Detection (OVAD) benchmark and the Visual Attributes in the Wild (VAW) dataset, and experiments indicate strong zero-shot performance. Ablation studies additionally demonstrate the effectiveness of each training step of our approach.

Authors:Krish Kabra, Guha Balakrishnan

Abstract: Perceptual metrics, like the Fr\'echet Inception Distance (FID), are widely used to assess the similarity between synthetically generated and ground truth (real) images. The key idea behind these metrics is to compute errors in a deep feature space that captures perceptually and semantically rich image features. Despite their popularity, the effect that different deep features and their design choices have on a perceptual metric has not been well studied. In this work, we perform a causal analysis linking differences in semantic attributes and distortions between face image distributions to Fr\'echet distances (FD) using several popular deep feature spaces. A key component of our analysis is the creation of synthetic counterfactual faces using deep face generators. Our experiments show that the FD is heavily influenced by its feature space's training dataset and objective function. For example, FD using features extracted from ImageNet-trained models heavily emphasize hats over regions like the eyes and mouth. Moreover, FD using features from a face gender classifier emphasize hair length more than distances in an identity (recognition) feature space. Finally, we evaluate several popular face generation models across feature spaces and find that StyleGAN2 consistently ranks higher than other face generators, except with respect to identity (recognition) features. This suggests the need for considering multiple feature spaces when evaluating generative models and using feature spaces that are tuned to nuances of the domain of interest.

Authors:Yi Zhang, Xiaoyu Shi, Dasong Li, Xiaogang Wang, Jian Wang, Hongsheng Li

Abstract: Diffusion Probabilistic Models (DPMs) have recently shown remarkable performance in image generation tasks, which are capable of generating highly realistic images. When adopting DPMs for image restoration tasks, the crucial aspect lies in how to integrate the conditional information to guide the DPMs to generate accurate and natural output, which has been largely overlooked in existing works. In this paper, we present a unified conditional framework based on diffusion models for image restoration. We leverage a lightweight UNet to predict initial guidance and the diffusion model to learn the residual of the guidance. By carefully designing the basic module and integration module for the diffusion model block, we integrate the guidance and other auxiliary conditional information into every block of the diffusion model to achieve spatially-adaptive generation conditioning. To handle high-resolution images, we propose a simple yet effective inter-step patch-splitting strategy to produce arbitrary-resolution images without grid artifacts. We evaluate our conditional framework on three challenging tasks: extreme low-light denoising, deblurring, and JPEG restoration, demonstrating its significant improvements in perceptual quality and the generalization to restoration tasks.

Authors:Haoxuan Xu, Songning Lai, Yang Yang

Abstract: Car detection, particularly through camera vision, has become a major focus in the field of computer vision and has gained widespread adoption. While current car detection systems are capable of good detection, reliable detection can still be challenging due to factors such as proximity between the car, light intensity, and environmental visibility. To address these issues, we propose a cross-domain car detection model that we apply to car recognition for autonomous driving and other areas. Our model includes several novelties: 1)Building a complete cross-domain target detection framework. 2)Developing an unpaired target domain picture generation module with an integrated convolutional attention mechanism. 3)Adopting Generalized Intersection over Union (GIOU) as the loss function of the target detection framework. 4)Designing an object detection model integrated with two-headed Convolutional Block Attention Module(CBAM). 5)Utilizing an effective data enhancement method. To evaluate the model's effectiveness, we performed a reduced will resolution process on the data in the SSLAD dataset and used it as the benchmark dataset for our task. Experimental results show that the performance of the cross-domain car target detection model improves by 40% over the model without our framework, and our improvements have a significant impact on cross-domain car recognition.

Authors:Imane Nedjar, Mohammed Brahimi, Said Mahmoudi, Khadidja Abi Ayad, Mohammed Amine Chikh

Abstract: Computer aided detection and diagnosis systems based on deep learning have shown promising performance in breast cancer detection. However, there are cases where the obtained results lack justification. In this study, our objective is to highlight the regions of interest used by a convolutional neural network (CNN) for classifying histological images as benign or malignant. We compare these regions with the regions identified by pathologists. To achieve this, we employed the VGG19 architecture and tested three visualization methods: Gradient, LRP Z, and LRP Epsilon. Additionally, we experimented with three pixel selection methods: Bins, K-means, and MeanShift. Based on the results obtained, the Gradient visualization method and the MeanShift selection method yielded satisfactory outcomes for visualizing the images.

Authors:Matan Levy, Rami Ben-Ari, Nir Darshan, Dani Lischinski

Abstract: Chats emerge as an effective user-friendly approach for information retrieval, and are successfully employed in many domains, such as customer service, healthcare, and finance. However, existing image retrieval approaches typically address the case of a single query-to-image round, and the use of chats for image retrieval has been mostly overlooked. In this work, we introduce ChatIR: a chat-based image retrieval system that engages in a conversation with the user to elicit information, in addition to an initial query, in order to clarify the user's search intent. Motivated by the capabilities of today's foundation models, we leverage Large Language Models to generate follow-up questions to an initial image description. These questions form a dialog with the user in order to retrieve the desired image from a large corpus. In this study, we explore the capabilities of such a system tested on a large dataset and reveal that engaging in a dialog yields significant gains in image retrieval. We start by building an evaluation pipeline from an existing manually generated dataset and explore different modules and training strategies for ChatIR. Our comparison includes strong baselines derived from related applications trained with Reinforcement Learning. Our system is capable of retrieving the target image from a pool of 50K images with over 78% success rate after 5 dialogue rounds, compared to 75% when questions are asked by humans, and 64% for a single shot text-to-image retrieval. Extensive evaluations reveal the strong capabilities and examine the limitations of CharIR under different settings.

Authors:Bo Hu, Yuheng Bu, José C. Príncipe

Abstract: This paper proposes the Hierarchical Functional Maximal Correlation Algorithm (HFMCA), a hierarchical methodology that characterizes dependencies across two hierarchical levels in multiview systems. By framing view similarities as dependencies and ensuring contrastivity by imposing orthonormality, HFMCA achieves faster convergence and increased stability in self-supervised learning. HFMCA defines and measures dependencies within image hierarchies, from pixels and patches to full images. We find that the network topology for approximating orthonormal basis functions aligns with a vanilla CNN, enabling the decomposition of density ratios between neighboring layers of feature maps. This approach provides powerful interpretability, revealing the resemblance between supervision and self-supervision through the lens of internal representations.

Authors:Ruizhi Shao, Jingxiang Sun, Cheng Peng, Zerong Zheng, Boyao Zhou, Hongwen Zhang, Yebin Liu

Abstract: Recent years have witnessed considerable achievements in editing images with text instructions. When applying these editors to dynamic scene editing, the new-style scene tends to be temporally inconsistent due to the frame-by-frame nature of these 2D editors. To tackle this issue, we propose Control4D, a novel approach for high-fidelity and temporally consistent 4D portrait editing. Control4D is built upon an efficient 4D representation with a 2D diffusion-based editor. Instead of using direct supervisions from the editor, our method learns a 4D GAN from it and avoids the inconsistent supervision signals. Specifically, we employ a discriminator to learn the generation distribution based on the edited images and then update the generator with the discrimination signals. For more stable training, multi-level information is extracted from the edited images and used to facilitate the learning of the generator. Experimental results show that Control4D surpasses previous approaches and achieves more photo-realistic and consistent 4D editing performances. The link to our project website is https://control4darxiv.github.io.

Authors:Alex Jinpeng Wang, Kevin Qinghong Lin, David Junhao Zhang, Stan Weixian Lei, Mike Zheng Shou

Abstract: This paper examines the problems of severe image-text misalignment and high redundancy in the widely-used large-scale Vision-Language Pre-Training (VLP) datasets. To address these issues, we propose an efficient and straightforward Vision-Language learning algorithm called TL;DR, which aims to compress the existing large VLP data into a small, high-quality set. Our approach consists of two major steps. First, a codebook-based encoder-decoder captioner is developed to select representative samples. Second, a new caption is generated to complement the original captions for selected samples, mitigating the text-image misalignment problem while maintaining uniqueness. As the result, TL;DR enables us to reduce the large dataset into a small set of high-quality data, which can serve as an alternative pre-training dataset. This algorithm significantly speeds up the time-consuming pretraining process. Specifically, TL;DR can compress the mainstream VLP datasets at a high ratio, e.g., reduce well-cleaned CC3M dataset from 2.82M to 0.67M ($\sim$24\%) and noisy YFCC15M from 15M to 2.5M ($\sim$16.7\%). Extensive experiments with three popular VLP models over seven downstream tasks show that VLP model trained on the compressed dataset provided by TL;DR can perform similar or even better results compared with training on the full-scale dataset. The code will be made available at \url{https://github.com/showlab/data-centric.vlp}.

Authors:Lijie Fan, Dilip Krishnan, Phillip Isola, Dina Katabi, Yonglong Tian

Abstract: Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which typically relies on data augmentations to prevent overfitting and shortcuts. However, in the CLIP training paradigm, data augmentations are exclusively applied to image inputs, while language inputs remain unchanged throughout the entire training process, limiting the exposure of diverse texts to the same image. In this paper, we introduce Language augmented CLIP (LaCLIP), a simple yet highly effective approach to enhance CLIP training through language rewrites. Leveraging the in-context learning capability of large language models, we rewrite the text descriptions associated with each image. These rewritten texts exhibit diversity in sentence structure and vocabulary while preserving the original key concepts and meanings. During training, LaCLIP randomly selects either the original texts or the rewritten versions as text augmentations for each image. Extensive experiments on CC3M, CC12M, RedCaps and LAION-400M datasets show that CLIP pre-training with language rewrites significantly improves the transfer performance without computation or memory overhead during training. Specifically for ImageNet zero-shot accuracy, LaCLIP outperforms CLIP by 8.2% on CC12M and 2.4% on LAION-400M. Code is available at https://github.com/LijieFan/LaCLIP.

Authors:Junxing Hu, Hongwen Zhang, Zerui Chen, Mengcheng Li, Yunlong Wang, Yebin Liu, Zhenan Sun

Abstract: Reconstructing hand-held objects from monocular RGB images is an appealing yet challenging task. In this task, contacts between hands and objects provide important cues for recovering the 3D geometry of the hand-held objects. Though recent works have employed implicit functions to achieve impressive progress, they ignore formulating contacts in their frameworks, which results in producing less realistic object meshes. In this work, we explore how to model contacts in an explicit way to benefit the implicit reconstruction of hand-held objects. Our method consists of two components: explicit contact prediction and implicit shape reconstruction. In the first part, we propose a new subtask of directly estimating 3D hand-object contacts from a single image. The part-level and vertex-level graph-based transformers are cascaded and jointly learned in a coarse-to-fine manner for more accurate contact probabilities. In the second part, we introduce a novel method to diffuse estimated contact states from the hand mesh surface to nearby 3D space and leverage diffused contact probabilities to construct the implicit neural representation for the manipulated object. Benefiting from estimating the interaction patterns between the hand and the object, our method can reconstruct more realistic object meshes, especially for object parts that are in contact with hands. Extensive experiments on challenging benchmarks show that the proposed method outperforms the current state of the arts by a great margin.

Authors:Shubham Goel, Georgios Pavlakos, Jathushan Rajasegaran, Angjoo Kanazawa, Jitendra Malik

Abstract: We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully "transformerized" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.

Authors:Neau Maëlic, Paulo Santos, Anne-Gwenn Bosser, Cédric Buche

Abstract: Learning to compose visual relationships from raw images in the form of scene graphs is a highly challenging task due to contextual dependencies, but it is essential in computer vision applications that depend on scene understanding. However, no current approaches in Scene Graph Generation (SGG) aim at providing useful graphs for downstream tasks. Instead, the main focus has primarily been on the task of unbiasing the data distribution for predicting more fine-grained relations. That being said, all fine-grained relations are not equally relevant and at least a part of them are of no use for real-world applications. In this work, we introduce the task of Efficient SGG that prioritizes the generation of relevant relations, facilitating the use of Scene Graphs in downstream tasks such as Image Generation. To support further approaches in this task, we present a new dataset, VG150-curated, based on the annotations of the popular Visual Genome dataset. We show through a set of experiments that this dataset contains more high-quality and diverse annotations than the one usually adopted by approaches in SGG. Finally, we show the efficiency of this dataset in the task of Image Generation from Scene Graphs. Our approach can be easily replicated to improve the quality of other Scene Graph Generation datasets.

Authors:Nazmul Karim, Umar Khalid, Mohsen Joneidi, Chen Chen, Nazanin Rahnavard

Abstract: Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts. Recent methods have tried to replicate the success by either training text-to-video (T2V) models on a very large number of text-video pairs or adapting T2I models on text-video pairs independently. Although the latter is computationally less expensive, it still takes a significant amount of time for per-video adaption. To address this issue, we propose SAVE, a novel spectral-shift-aware adaptation framework, in which we fine-tune the spectral shift of the parameter space instead of the parameters themselves. Specifically, we take the spectral decomposition of the pre-trained T2I weights and only control the change in the corresponding singular values, i.e. spectral shift, while freezing the corresponding singular vectors. To avoid drastic drift from the original T2I weights, we introduce a spectral shift regularizer that confines the spectral shift to be more restricted for large singular values and more relaxed for small singular values. Since we are only dealing with spectral shifts, the proposed method reduces the adaptation time significantly (approx. 10 times) and has fewer resource constrains for training. Such attributes posit SAVE to be more suitable for real-world applications, e.g. editing undesirable content during video streaming. We validate the effectiveness of SAVE with an extensive experimental evaluation under different settings, e.g. style transfer, object replacement, privacy preservation, etc.

Authors:Pengzhi Li, QInxuan Huang, Yikang Ding, Zhiheng Li

Abstract: Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining consistency between the subject and the background remains challenging. In this paper, we propose LayerDiffusion, a semantic-based layered controlled image editing method. Our method enables non-rigid editing and attribute modification of specific subjects while preserving their unique characteristics and seamlessly integrating them into new backgrounds. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy combined with layered diffusion training. During the diffusion process, an iterative guidance strategy is used to generate a final image that aligns with the textual description. Experimental results demonstrate the effectiveness of our method in generating highly coherent images that closely align with the given textual description. The edited images maintain a high similarity to the features of the input image and surpass the performance of current leading image editing methods. LayerDiffusion opens up new possibilities for controllable image editing.

Authors:Kangjun Liu, Ke Chen, Yaowei Wang, Kui Jia

Abstract: Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks. However, existing methods for semantic classification typically employ pre-defined target codes such as the one-hot and the Hadamard codes, which can either fail or be less flexible to model inter-class correlation. In light of this, this paper introduces a novel learnable target coding as an auxiliary regularization of deep representation learning, which can not only incorporate latent dependency across classes but also impose geometric properties of target codes into representation space. Specifically, a margin-based triplet loss and a correlation consistency loss on the proposed target codes are designed to encourage more discriminative representations owing to enlarging between-class margins in representation space and favoring equal semantic correlation of learnable target codes respectively. Experimental results on several popular visual classification and retrieval benchmarks can demonstrate the effectiveness of our method on improving representation learning, especially for imbalanced data.

Authors:Kangjun Liu, Ke Chen, Lihua Guo, Yaowei Wang, Kui Jia

Abstract: Mixup style data augmentation algorithms have been widely adopted in various tasks as implicit network regularization on representation learning to improve model generalization, which can be achieved by a linear interpolation of labeled samples in input or feature space as well as target space. Inspired by good robustness of alternative dropout strategies against over-fitting on limited patterns of training samples, this paper introduces a novel concept of ShuffleMix -- Shuffle of Mixed hidden features, which can be interpreted as a kind of dropout operation in feature space. Specifically, our ShuffleMix method favors a simple linear shuffle of randomly selected feature channels for feature mixup in-between training samples to leverage semantic interpolated supervision signals, which can be extended to a generalized shuffle operation via additionally combining linear interpolations of intra-channel features. Compared to its direct competitor of feature augmentation -- the Manifold Mixup, the proposed ShuffleMix can gain superior generalization, owing to imposing more flexible and smooth constraints on generating samples and achieving regularization effects of channel-wise feature dropout. Experimental results on several public benchmarking datasets of single-label and multi-label visual classification tasks can confirm the effectiveness of our method on consistently improving representations over the state-of-the-art mixup augmentation.

Authors:Fei Wang, Jun Cheng

Abstract: Decoders play significant roles in recovering scene depths. However, the decoders used in previous works ignore the propagation of multilevel lossless fine-grained information, cannot adaptively capture local and global information in parallel, and cannot perform sufficient global statistical analyses on the final output disparities. In addition, the process of mapping from a low-resolution feature space to a high-resolution feature space is a one-to-many problem that may have multiple solutions. Therefore, the quality of the recovered depth map is low. To this end, we propose a high-quality decoder (HQDec), with which multilevel near-lossless fine-grained information, obtained by the proposed adaptive axial-normalized position-embedded channel attention sampling module (AdaAxialNPCAS), can be adaptively incorporated into a low-resolution feature map with high-level semantics utilizing the proposed adaptive information exchange scheme. In the HQDec, we leverage the proposed adaptive refinement module (AdaRM) to model the local and global dependencies between pixels in parallel and utilize the proposed disparity attention module to model the distribution characteristics of disparity values from a global perspective. To recover fine-grained high-resolution features with maximal accuracy, we adaptively fuse the high-frequency information obtained by constraining the upsampled solution space utilizing the local and global dependencies between pixels into the high-resolution feature map generated from the nonlearning method. Extensive experiments demonstrate that each proposed component improves the quality of the depth estimation results over the baseline results, and the developed approach achieves state-of-the-art results on the KITTI and DDAD datasets. The code and models will be publicly available at \href{https://github.com/fwucas/HQDec}{HQDec}.

Authors:Yadong Wang, Xiangzhi Bai

Abstract: Most existing deep learning-based image restoration methods usually aim to remove degradation with uniform spatial distribution and constant intensity, making insufficient use of degradation prior knowledge. Here we bootstrap the deep neural networks to suppress complex image degradation whose intensity is spatially variable, through utilizing prior knowledge from degraded images. Specifically, we propose an ingenious and efficient multi-frame image restoration network (DparNet) with wide & deep architecture, which integrates degraded images and prior knowledge of degradation to reconstruct images with ideal clarity and stability. The degradation prior is directly learned from degraded images in form of key degradation parameter matrix, with no requirement of any off-site knowledge. The wide & deep architecture in DparNet enables the learned parameters to directly modulate the final restoring results, boosting spatial & intensity adaptive image restoration. We demonstrate the proposed method on two representative image restoration applications: image denoising and suppression of atmospheric turbulence effects in images. Two large datasets, containing 109,536 and 49,744 images respectively, were constructed to support our experiments. The experimental results show that our DparNet significantly outperform SoTA methods in restoration performance and network efficiency. More importantly, by utilizing the learned degradation parameters via wide & deep learning, we can improve the PSNR of image restoration by 0.6~1.1 dB with less than 2% increasing in model parameter numbers and computational complexity. Our work suggests that degraded images may hide key information of the degradation process, which can be utilized to boost spatial & intensity adaptive image restoration.

Authors:Ziao Li, Junyi Wang, Guhong Nie

Abstract: Recently, significant achievements have been made in skeleton-based human action recognition with the emergence of graph convolutional networks (GCNs). However, the state-of-the-art (SOTA) models used for this task focus on constructing more complex higher-order connections between joint nodes to describe skeleton information, which leads to complex inference processes and high computational costs, resulting in reduced model's practicality. To address the slow inference speed caused by overly complex model structures, we introduce re-parameterization and over-parameterization techniques to GCNs, and propose two novel high-performance inference graph convolutional networks, namely HPI-GCN-RP and HPI-GCN-OP. HPI-GCN-RP uses re-parameterization technique to GCNs to achieve a higher inference speed with competitive model performance. HPI-GCN-OP further utilizes over-parameterization technique to bring significant performance improvement with inference speed slightly decreased. Experimental results on the two skeleton-based action recognition datasets demonstrate the effectiveness of our approach. Our HPI-GCN-OP achieves an accuracy of 93% on the cross-subject split of the NTU-RGB+D 60 dataset, and 90.1% on the cross-subject benchmark of the NTU-RGB+D 120 dataset and is 4.5 times faster than HD-GCN at the same accuracy.

Authors:Jianfei Yang, Hanjie Qian, Yuecong Xu, Lihua Xie

Abstract: Unsupervised domain adaptation (UDA) involves adapting a model trained on a label-rich source domain to an unlabeled target domain. However, in real-world scenarios, the absence of target-domain labels makes it challenging to evaluate the performance of deep models after UDA. Additionally, prevailing UDA methods typically rely on adversarial training and self-training, which could lead to model degeneration and negative transfer, further exacerbating the evaluation problem. In this paper, we propose a novel metric called the \textit{Transfer Score} to address these issues. The transfer score enables the unsupervised evaluation of domain adaptation models by assessing the spatial uniformity of the classifier via model parameters, as well as the transferability and discriminability of the feature space. Based on unsupervised evaluation using our metric, we achieve three goals: (1) selecting the most suitable UDA method from a range of available options, (2) optimizing hyperparameters of UDA models to prevent model degeneration, and (3) identifying the epoch at which the adapted model performs optimally. Our work bridges the gap between UDA research and practical UDA evaluation, enabling a realistic assessment of UDA model performance. We validate the effectiveness of our metric through extensive empirical studies conducted on various public datasets. The results demonstrate the utility of the transfer score in evaluating UDA models and its potential to enhance the overall efficacy of UDA techniques.

Authors:Supeng Wang, Yuxi Li, Ming Xie, Mingmin Chi, Yabiao Wang, Chengjie Wang, Wenbing Zhu

Abstract: Change detection is a widely adopted technique in remote sense imagery (RSI) analysis in the discovery of long-term geomorphic evolution. To highlight the areas of semantic changes, previous effort mostly pays attention to learning representative feature descriptors of a single image, while the difference information is either modeled with simple difference operations or implicitly embedded via feature interactions. Nevertheless, such difference modeling can be noisy since it suffers from non-semantic changes and lacks explicit guidance from image content or context. In this paper, we revisit the importance of feature difference for change detection in RSI, and propose a series of operations to fully exploit the difference information: Alignment, Perturbation and Decoupling (APD). Firstly, alignment leverages contextual similarity to compensate for the non-semantic difference in feature space. Next, a difference module trained with semantic-wise perturbation is adopted to learn more generalized change estimators, which reversely bootstraps feature extraction and prediction. Finally, a decoupled dual-decoder structure is designed to predict semantic changes in both content-aware and content-agnostic manners. Extensive experiments are conducted on benchmarks of LEVIR-CD, WHU-CD and DSIFN-CD, demonstrating our proposed operations bring significant improvement and achieve competitive results under similar comparative conditions. Code is available at https://github.com/wangsp1999/CD-Research/tree/main/openAPD

Authors:Yi Tu, Ya Guo, Huan Chen, Jinyang Tang

Abstract: Visually-rich Document Understanding (VrDU) has attracted much research attention over the past years. Pre-trained models on a large number of document images with transformer-based backbones have led to significant performance gains in this field. The major challenge is how to fusion the different modalities (text, layout, and image) of the documents in a unified model with different pre-training tasks. This paper focuses on improving text-layout interactions and proposes a novel multi-modal pre-training model, LayoutMask. LayoutMask uses local 1D position, instead of global 1D position, as layout input and has two pre-training objectives: (1) Masked Language Modeling: predicting masked tokens with two novel masking strategies; (2) Masked Position Modeling: predicting masked 2D positions to improve layout representation learning. LayoutMask can enhance the interactions between text and layout modalities in a unified model and produce adaptive and robust multi-modal representations for downstream tasks. Experimental results show that our proposed method can achieve state-of-the-art results on a wide variety of VrDU problems, including form understanding, receipt understanding, and document image classification.

Authors:Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie Zhou, Jiwen Lu

Abstract: In this paper, we propose an accurate data-free post-training quantization framework of diffusion models (ADP-DM) for efficient image generation. Conventional data-free quantization methods learn shared quantization functions for tensor discretization regardless of the generation timesteps, while the activation distribution differs significantly across various timesteps. The calibration images are acquired in random timesteps which fail to provide sufficient information for generalizable quantization function learning. Both issues cause sizable quantization errors with obvious image generation performance degradation. On the contrary, we design group-wise quantization functions for activation discretization in different timesteps and sample the optimal timestep for informative calibration image generation, so that our quantized diffusion model can reduce the discretization errors with negligible computational overhead. Specifically, we partition the timesteps according to the importance weights of quantization functions in different groups, which are optimized by differentiable search algorithms. We also select the optimal timestep for calibration image generation by structural risk minimizing principle in order to enhance the generalization ability in the deployment of quantized diffusion model. Extensive experimental results show that our method outperforms the state-of-the-art post-training quantization of diffusion model by a sizable margin with similar computational cost.

Authors:Daegyu Kim, Chaehun Shin, Jooyoung Choi, Dahuin Jung, Sungroh Yoon

Abstract: Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity and anti-detection ability over cover images. However, they create relatively unrealistic stego images because of the inherent limitations of generative models. We propose Diffusion-Stego, a generative steganography approach based on diffusion models which outperform other generative models in image generation. Diffusion-Stego projects secret messages into latent noise of diffusion models and generates stego images with an iterative denoising process. Since the naive hiding of secret messages into noise boosts visual degradation and decreases extracted message accuracy, we introduce message projection, which hides messages into noise space while addressing these issues. We suggest three options for message projection to adjust the trade-off between extracted message accuracy, anti-detection ability, and image quality. Diffusion-Stego is a training-free approach, so we can apply it to pre-trained diffusion models which generate high-quality images, or even large-scale text-to-image models, such as Stable diffusion. Diffusion-Stego achieved a high capacity of messages (3.0 bpp of binary messages with 98% accuracy, and 6.0 bpp with 90% accuracy) as well as high quality (with a FID score of 2.77 for 1.0 bpp on the FFHQ 64$\times$64 dataset) that makes it challenging to distinguish from real images in the PNG format.

Authors:Yuechen Zhang, Jinbo Xing, Eric Lo, Jiaya Jia

Abstract: Recent diffusion model advancements have enabled high-fidelity images to be generated using text prompts. However, a domain gap exists between generated images and real-world images, which poses a challenge in generating high-quality variations of real-world images. Our investigation uncovers that this domain gap originates from a latents' distribution gap in different diffusion processes. To address this issue, we propose a novel inference pipeline called Real-world Image Variation by ALignment (RIVAL) that utilizes diffusion models to generate image variations from a single image exemplar. Our pipeline enhances the generation quality of image variations by aligning the image generation process to the source image's inversion chain. Specifically, we demonstrate that step-wise latent distribution alignment is essential for generating high-quality variations. To attain this, we design a cross-image self-attention injection for feature interaction and a step-wise distribution normalization to align the latent features. Incorporating these alignment processes into a diffusion model allows RIVAL to generate high-quality image variations without further parameter optimization. Our experimental results demonstrate that our proposed approach outperforms existing methods with respect to semantic-condition similarity and perceptual quality. Furthermore, this generalized inference pipeline can be easily applied to other diffusion-based generation tasks, such as image-conditioned text-to-image generation and example-based image inpainting.

Authors:Jin Yuan, Yang Zhang, Yangzhou Du, Zhongchao Shi, Xin Geng, Jianping Fan, Yong Rui

Abstract: In recent years, deep models have achieved remarkable success in many vision tasks. Unfortunately, their performance largely depends on intensive training samples. In contrast, human beings typically perform hybrid learning, e.g., spontaneously integrating structured knowledge for cross-domain recognition or on a much smaller amount of data samples for few-shot learning. Thus it is very attractive to extend hybrid learning for the computer vision tasks by seamlessly integrating structured knowledge with data samples to achieve more effective representation learning. However, such a hybrid learning approach remains a great challenge due to the huge gap between the structured knowledge and the deep features (learned from data samples) on both dimensions and knowledge granularity. In this paper, a novel Epistemic Graph Layer (EGLayer) is developed to enable hybrid learning, such that the information can be exchanged more effectively between the deep features and a structured knowledge graph. Our EGLayer is composed of three major parts: (a) a local graph module to establish a local prototypical graph through the learned deep features, i.e., aligning the deep features with the structured knowledge graph at the same granularity; (b) a query aggregation model to aggregate useful information from the local graphs, and using such representations to compute their similarity with global node embeddings for final prediction; and (c) a novel correlation loss function to constrain the linear consistency between the local and global adjacency matrices.

Authors:Wenshuo Chen, Xiang Zhou, Zhengdi Yu, Zhaoyu Zheng, Weixi Gu, Kai Zhang

Abstract: Estimating human pose from video is a task that receives considerable attention due to its applicability in numerous 3D fields. The complexity of prior knowledge of human body movements poses a challenge to neural network models in the task of regressing keypoints. In this paper, we address this problem by incorporating motion prior in an adversarial way. Different from previous methods, we propose to decompose holistic motion prior to joint motion prior, making it easier for neural networks to learn from prior knowledge thereby boosting the performance on the task. We also utilize a novel regularization loss to balance accuracy and smoothness introduced by motion prior. Our method achieves 9\% lower PA-MPJPE and 29\% lower acceleration error than previous methods tested on 3DPW. The estimator proves its robustness by achieving impressive performance on in-the-wild dataset.

Authors:Linhao Qu, Xiaoyuan Luo, Kexue Fu, Manning Wang, Zhijian Song

Abstract: This paper introduces the novel concept of few-shot weakly supervised learning for pathology Whole Slide Image (WSI) classification, denoted as FSWC. A solution is proposed based on prompt learning and the utilization of a large language model, GPT-4. Since a WSI is too large and needs to be divided into patches for processing, WSI classification is commonly approached as a Multiple Instance Learning (MIL) problem. In this context, each WSI is considered a bag, and the obtained patches are treated as instances. The objective of FSWC is to classify both bags and instances with only a limited number of labeled bags. Unlike conventional few-shot learning problems, FSWC poses additional challenges due to its weak bag labels within the MIL framework. Drawing inspiration from the recent achievements of vision-language models (V-L models) in downstream few-shot classification tasks, we propose a two-level prompt learning MIL framework tailored for pathology, incorporating language prior knowledge. Specifically, we leverage CLIP to extract instance features for each patch, and introduce a prompt-guided pooling strategy to aggregate these instance features into a bag feature. Subsequently, we employ a small number of labeled bags to facilitate few-shot prompt learning based on the bag features. Our approach incorporates the utilization of GPT-4 in a question-and-answer mode to obtain language prior knowledge at both the instance and bag levels, which are then integrated into the instance and bag level language prompts. Additionally, a learnable component of the language prompts is trained using the available few-shot labeled data. We conduct extensive experiments on three real WSI datasets encompassing breast cancer, lung cancer, and cervical cancer, demonstrating the notable performance of the proposed method in bag and instance classification. All codes will be made publicly accessible.

Authors:Xiang Zhang, Yan Lu, Huan Yan, Jingyang Huang, Yusheng Ji, Yu Gu

Abstract: Because of the ambiguous and subjective property of the facial expression recognition (FER) task, the label noise is widely existing in the FER dataset. For this problem, in the training phase, current FER methods often directly predict whether the label of the input image is noised or not, aiming to reduce the contribution of the noised data in training. However, we argue that this kind of method suffers from the low reliability of such noise data decision operation. It makes that some mistakenly abounded clean data are not utilized sufficiently and some mistakenly kept noised data disturbing the model learning process. In this paper, we propose a more reliable noise-label suppression method called ReSup (Reliable label noise Suppression for FER). First, instead of directly predicting noised or not, ReSup makes the noise data decision by modeling the distribution of noise and clean labels simultaneously according to the disagreement between the prediction and the target. Specifically, to achieve optimal distribution modeling, ReSup models the similarity distribution of all samples. To further enhance the reliability of our noise decision results, ReSup uses two networks to jointly achieve noise suppression. Specifically, ReSup utilize the property that two networks are less likely to make the same mistakes, making two networks swap decisions and tending to trust decisions with high agreement. Extensive experiments on three popular benchmarks show that the proposed method significantly outperforms state-of-the-art noisy label FER methods by 3.01% on FERPlus becnmarks. Code: https://github.com/purpleleaves007/FERDenoise

Authors:Xin Hua, Zhijiang Du, Hongjian Yu, Jixin Maa

Abstract: Magnetic resonance imaging (MRI) is a valuable clinical tool for displaying anatomical structures and aiding in accurate diagnosis. Medical image super-resolution (SR) reconstruction using deep learning techniques can enhance lesion analysis and assist doctors in improving diagnostic efficiency and accuracy. However, existing deep learning-based SR methods predominantly rely on convolutional neural networks (CNNs), which inherently limit the expressive capabilities of these models and therefore make it challenging to discover potential relationships between different image features. To overcome this limitation, we propose an A-network that utilizes multiple convolution operator feature extraction modules (MCO) for extracting image features using multiple convolution operators. These extracted features are passed through multiple sets of cross-feature extraction modules (MSC) to highlight key features through inter-channel feature interactions, enabling subsequent feature learning. An attention-based sparse graph neural network module is incorporated to establish relationships between pixel features, learning which adjacent pixels have the greatest impact on determining the features to be filled. To evaluate our model's effectiveness, we conducted experiments using different models on data generated from multiple datasets with different degradation multiples, and the experimental results show that our method is a significant improvement over the current state-of-the-art methods.

Authors:Xuejing Liu, Wei Tang, Jinghui Lu, Rui Zhao, Zhaojun Guo, Fei Tan

Abstract: Recent advancements in multimodal foundation models (e.g., CLIP) have excelled in zero-shot generalization. Prompt tuning involved in the knowledge transfer from foundation models to downstream tasks has gained significant attention recently. Existing prompt-tuning methods in cross-modal learning, however, either solely focus on language branch, or learn vision-language interaction in a shallow mechanism. In this context, we propose a Deeply coupled Cross-modal Prompt learning (DCP) method based on CLIP. DCP flexibly accommodates the interplay between vision and language with a Cross-Modal Prompt Attention (CMPA) mechanism, which enables the mutual exchange of respective representation through a well-connected multi-head attention module progressively and strongly. We then conduct comprehensive few-shot learning experiments on 11 image classification datasets and analyze the robustness to domain shift as well. Thorough experimental analysis evidently demonstrates the superb few-shot generalization and compelling domain adaption capacity of a well-executed DCP. The code can be found at https://github.com/GingL/CMPA.

Authors:Kang Han, Wei Xiang, Lu Yu

Abstract: Neural radiance fields (NeRFs) are able to synthesize realistic novel views from multi-view images captured from distinct positions and perspectives. In NeRF's rendering pipeline, neural networks are used to represent a scene independently or transform queried learnable feature vector of a point to the expected color or density. With the aid of geometry guides either in occupancy grids or proposal networks, the number of neural network evaluations can be reduced from hundreds to dozens in the standard volume rendering framework. Instead of rendering yielded color after neural network evaluation, we propose to render the queried feature vectors of a ray first and then transform the rendered feature vector to the final pixel color by a neural network. This fundamental change to the standard volume rendering framework requires only one single neural network evaluation to render a pixel, which substantially lowers the high computational complexity of the rendering framework attributed to a large number of neural network evaluations. Consequently, we can use a comparably larger neural network to achieve a better rendering quality while maintaining the same training and rendering time costs. Our model achieves the state-of-the-art rendering quality on both synthetic and real-world datasets while requiring a training time of several minutes.

Authors:Yuexiong Ding, Xiaowei Luo

Abstract: Currently, object detection applications in construction are almost based on pure 2D data (both image and annotation are 2D-based), resulting in the developed artificial intelligence (AI) applications only applicable to some scenarios that only require 2D information. However, most advanced applications usually require AI agents to perceive 3D spatial information, which limits the further development of the current computer vision (CV) in construction. The lack of 3D annotated datasets for construction object detection worsens the situation. Therefore, this study creates and releases a virtual dataset with 3D annotations named VCVW-3D, which covers 15 construction scenes and involves ten categories of construction vehicles and workers. The VCVW-3D dataset is characterized by multi-scene, multi-category, multi-randomness, multi-viewpoint, multi-annotation, and binocular vision. Several typical 2D and monocular 3D object detection models are then trained and evaluated on the VCVW-3D dataset to provide a benchmark for subsequent research. The VCVW-3D is expected to bring considerable economic benefits and practical significance by reducing the costs of data construction, prototype development, and exploration of space-awareness applications, thus promoting the development of CV in construction, especially those of 3D applications.

Authors:Yue Fan, Ivan Skorokhodov, Oleg Voynov, Savva Ignatyev, Evgeny Burnaev, Peter Wonka, Yiqun Wang

Abstract: We develop a method that recovers the surface, materials, and illumination of a scene from its posed multi-view images. In contrast to prior work, it does not require any additional data and can handle glossy objects or bright lighting. It is a progressive inverse rendering approach, which consists of three stages. First, we reconstruct the scene radiance and signed distance function (SDF) with our novel regularization strategy for specular reflections. Our approach considers both the diffuse and specular colors, which allows for handling complex view-dependent lighting effects for surface reconstruction. Second, we distill light visibility and indirect illumination from the learned SDF and radiance field using learnable mapping functions. Third, we design a method for estimating the ratio of incoming direct light represented via Spherical Gaussians reflected in a specular manner and then reconstruct the materials and direct illumination of the scene. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art in recovering surfaces, materials, and lighting without relying on any additional data.

Authors:Yuexiong Ding, Xiaowei Luo

Abstract: Accident of struck-by machines is one of the leading causes of casualties on construction sites. Monitoring workers' proximities to avoid human-machine collisions has aroused great concern in construction safety management. Existing methods are either too laborious and costly to apply extensively, or lacking spatial perception for accurate monitoring. Therefore, this study proposes a novel framework for proximity monitoring using only an ordinary 2D camera to realize real-time human-machine collision warning, which is designed to integrate a monocular 3D object detection model to perceive spatial information from 2D images and a post-processing classification module to identify the proximity as four predefined categories: Dangerous, Potentially Dangerous, Concerned, and Safe. A virtual dataset containing 22000 images with 3D annotations is constructed and publicly released to facilitate the system development and evaluation. Experimental results show that the trained 3D object detection model achieves 75% loose AP within 20 meters. Besides, the implemented system is real-time and camera carrier-independent, achieving an F1 of roughly 0.8 within 50 meters under specified settings for machines of different sizes. This study preliminarily reveals the potential and feasibility of proximity monitoring using only a 2D camera, providing a new promising and economical way for early warning of human-machine collisions.

Authors:Zhongxi Chen, Ke Sun, Xianming Lin, Rongrong Ji

Abstract: Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods primarily employ semantic segmentation, which suffers from overconfident incorrect predictions. In this paper, we propose a new paradigm that treats COD as a conditional mask-generation task leveraging diffusion models. Our method, dubbed CamoDiffusion, employs the denoising process of diffusion models to iteratively reduce the noise of the mask. Due to the stochastic sampling process of diffusion, our model is capable of sampling multiple possible predictions from the mask distribution, avoiding the problem of overconfident point estimation. Moreover, we develop specialized learning strategies that include an innovative ensemble approach for generating robust predictions and tailored forward diffusion methods for efficient training, specifically for the COD task. Extensive experiments on three COD datasets attest the superior performance of our model compared to existing state-of-the-art methods, particularly on the most challenging COD10K dataset, where our approach achieves 0.019 in terms of MAE.

Authors:Jianqiu Chen, Mingshan Sun, Tianpeng Bao, Rui Zhao, Liwei Wu, Zhenyu He

Abstract: Most existing learning-based pose estimation methods are typically developed for non-zero-shot scenarios, where they can only estimate the poses of objects present in the training dataset. This setting restricts their applicability to unseen objects in the training phase. In this paper, we introduce a fully zero-shot pose estimation pipeline that leverages the 3D models of objects as clues. Specifically, we design a two-step pipeline consisting of 3D model-based zero-shot instance segmentation and a zero-shot pose estimator. For the first step, there is a novel way to perform zero-shot instance segmentation based on the 3D models instead of text descriptions, which can handle complex properties of unseen objects. For the second step, we utilize a hierarchical geometric structure matching mechanism to perform zero-shot pose estimation which is 10 times faster than the current render-based method. Extensive experimental results on the seven core datasets on the BOP challenge show that the proposed method outperforms the zero-shot state-of-the-art method with higher speed and lower computation cost.

Authors:Nariki Tanaka, Hiroshi Kera, Kazuhiko Kawamoto

Abstract: Using Fourier analysis, we explore the robustness and vulnerability of graph convolutional neural networks (GCNs) for skeleton-based action recognition. We adopt a joint Fourier transform (JFT), a combination of the graph Fourier transform (GFT) and the discrete Fourier transform (DFT), to examine the robustness of adversarially-trained GCNs against adversarial attacks and common corruptions. Experimental results with the NTU RGB+D dataset reveal that adversarial training does not introduce a robustness trade-off between adversarial attacks and low-frequency perturbations, which typically occurs during image classification based on convolutional neural networks. This finding indicates that adversarial training is a practical approach to enhancing robustness against adversarial attacks and common corruptions in skeleton-based action recognition. Furthermore, we find that the Fourier approach cannot explain vulnerability against skeletal part occlusion corruption, which highlights its limitations. These findings extend our understanding of the robustness of GCNs, potentially guiding the development of more robust learning methods for skeleton-based action recognition.

Authors:Qingsheng Wang, Lingqiao Liu, Chenchen Jing, Hao Chen, Guoqiang Liang, Peng Wang, Chunhua Shen

Abstract: Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the challenges is to model attributes interacted with different objects, e.g., the attribute ``wet" in ``wet apple" and ``wet cat" is different. As a solution, we provide analysis and argue that attributes are conditioned on the recognized object and input image and explore learning conditional attribute embeddings by a proposed attribute learning framework containing an attribute hyper learner and an attribute base learner. By encoding conditional attributes, our model enables to generate flexible attribute embeddings for generalization from seen to unseen compositions. Experiments on CZSL benchmarks, including the more challenging C-GQA dataset, demonstrate better performances compared with other state-of-the-art approaches and validate the importance of learning conditional attributes. Code is available at https://github.com/wqshmzh/CANet-CZSL

Authors:Issa Mouawad, Nikolas Brasch, Fabian Manhardt, Federico Tombari, Francesca Odone

Abstract: For autonomous vehicles, driving safely is highly dependent on the capability to correctly perceive the environment in 3D space, hence the task of 3D object detection represents a fundamental aspect of perception. While 3D sensors deliver accurate metric perception, monocular approaches enjoy cost and availability advantages that are valuable in a wide range of applications. Unfortunately, training monocular methods requires a vast amount of annotated data. Interestingly, self-supervised approaches have recently been successfully applied to ease the training process and unlock access to widely available unlabelled data. While related research leverages different priors including LIDAR scans and stereo images, such priors again limit usability. Therefore, in this work, we propose a novel approach to self-supervise 3D object detection purely from RGB sequences alone, leveraging multi-view constraints and weak labels. Our experiments on KITTI 3D dataset demonstrate performance on par with state-of-the-art self-supervised methods using LIDAR scans or stereo images.

Authors:Jiaxin Lu, Yifan Sun, Qixing Huang

Abstract: Automated assembly of 3D fractures is essential in orthopedics, archaeology, and our daily life. This paper presents Jigsaw, a novel framework for assembling physically broken 3D objects from multiple pieces. Our approach leverages hierarchical features of global and local geometry to match and align the fracture surfaces. Our framework consists of three components: (1) surface segmentation to separate fracture and original parts, (2) multi-parts matching to find correspondences among fracture surface points, and (3) robust global alignment to recover the global poses of the pieces. We show how to jointly learn segmentation and matching and seamlessly integrate feature matching and rigidity constraints. We evaluate Jigsaw on the Breaking Bad dataset and achieve superior performance compared to state-of-the-art methods. Our method also generalizes well to diverse fracture modes, objects, and unseen instances. To the best of our knowledge, this is the first learning-based method designed specifically for 3D fracture assembly over multiple pieces.

Authors:Mengzhao Chen, Wenqi Shao, Peng Xu, Mingbao Lin, Kaipeng Zhang, Fei Chao, Rongrong Ji, Yu Qiao, Ping Luo

Abstract: Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to carefully handcraft a compression rate (i.e. number of tokens to remove), which is tedious and leads to sub-optimal performance. To tackle this problem, we propose Differentiable Compression Rate (DiffRate), a novel token compression method that has several appealing properties prior arts do not have. First, DiffRate enables propagating the loss function's gradient onto the compression ratio, which is considered as a non-differentiable hyperparameter in previous work. In this case, different layers can automatically learn different compression rates layer-wisely without extra overhead. Second, token pruning and merging can be naturally performed simultaneously in DiffRate, while they were isolated in previous works. Third, extensive experiments demonstrate that DiffRate achieves state-of-the-art performance. For example, by applying the learned layer-wise compression rates to an off-the-shelf ViT-H (MAE) model, we achieve a 40% FLOPs reduction and a 1.5x throughput improvement, with a minor accuracy drop of 0.16% on ImageNet without fine-tuning, even outperforming previous methods with fine-tuning. Codes and models are available at https://github.com/OpenGVLab/DiffRate.

Authors:Hyunsoo Lee, Minsoo Kang, Bohyung Han

Abstract: We present a novel algorithm for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our method aims to generate a target image by selectively editing the regions of interest in a source image, defined by a modifying text, while preserving the remaining parts. In contrast to existing techniques that solely rely on a target prompt, we introduce a new score function, which considers both a source prompt and a source image, tailored to address specific translation tasks. To this end, we derive the conditional score function in a principled manner, decomposing it into a standard score and a guiding term for target image generation. For the gradient computation, we adopt a Gaussian distribution of the posterior distribution, estimating its mean and variance without requiring additional training. In addition, to enhance the conditional score guidance, we incorporate a simple yet effective mixup method. This method combines two cross-attention maps derived from the source and target latents, promoting the generation of the target image by a desirable fusion of the original parts in the source image and the edited regions aligned with the target prompt. Through comprehensive experiments, we demonstrate that our approach achieves outstanding image-to-image translation performance on various tasks.

Authors:Piotr Wzorek, Tomasz Kryjak

Abstract: Despite the dynamic development of computer vision algorithms, the implementation of perception and control systems for autonomous vehicles such as drones and self-driving cars still poses many challenges. A video stream captured by traditional cameras is often prone to problems such as motion blur or degraded image quality due to challenging lighting conditions. In addition, the frame rate - typically 30 or 60 frames per second - can be a limiting factor in certain scenarios. Event cameras (DVS -- Dynamic Vision Sensor) are a potentially interesting technology to address the above mentioned problems. In this paper, we compare two methods of processing event data by means of deep learning for the task of pedestrian detection. We used a representation in the form of video frames, convolutional neural networks and asynchronous sparse convolutional neural networks. The results obtained illustrate the potential of event cameras and allow the evaluation of the accuracy and efficiency of the methods used for high-resolution (1280 x 720 pixels) footage.

Authors:Mengtian Li, Yi Dong, Minxuan Lin, Haibin Huang, Pengfei Wan, Chongyang Ma

Abstract: In this work, we introduce a new approach for artistic face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high-quality stylized faces with diverse styles and accurate facial reconstruction. Our proposed framework, MMFS, supports multi-modal face stylization by leveraging the strengths of StyleGAN and integrates it into an encoder-decoder architecture. Specifically, we use the mid-resolution and high-resolution layers of StyleGAN as the decoder to generate high-quality faces, while aligning its low-resolution layer with the encoder to extract and preserve input facial details. We also introduce a two-stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces. In the second stage, the entire network is fine-tuned with artistic data for stylized face generation. To enable the fine-tuned model to be applied in zero-shot and one-shot stylization tasks, we train an additional mapping network from the large-scale Contrastive-Language-Image-Pre-training (CLIP) space to a latent $w+$ space of fine-tuned StyleGAN. Qualitative and quantitative experiments show that our framework achieves superior face stylization performance in both one-shot and zero-shot stylization tasks, outperforming state-of-the-art methods by a large margin.

Authors:Shuai Zhao, Xiaohan Wang, Linchao Zhu, Yi Yang

Abstract: Misalignment between the outputs of a vision-language (VL) model and task goal hinders its deployment. This issue can worsen when there are distribution shifts between the training and test data. To address this problem, prevailing fully test-time adaptation~(TTA) methods bootstrap themselves through entropy minimization. However, minimizing the entropy of the predictions makes the model overfit to incorrect output distributions of itself. In this work, we propose TTA with feedback to avoid such overfitting and align the model with task goals. Specifically, we adopt CLIP as reward model to provide feedback for VL models during test time in various tasks, including image classification, image-text retrieval, and image captioning. Given a single test sample, the model aims to maximize CLIP reward through reinforcement learning. We adopt a reward design with the average CLIP score of sampled candidates as the baseline. This design is simple and surprisingly effective when combined with various task-specific sampling strategies. The entire system is flexible, allowing the reward model to be extended with multiple CLIP models. Plus, a momentum buffer can be used to memorize and leverage the learned knowledge from multiple test samples. Extensive experiments demonstrate that our method significantly improves different VL models after TTA.

Authors:Weihuang Liu, Xi Shen, Chi-Man Pun, Xiaodong Cun

Abstract: Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied on domain-specific solutions to address accuracy and robustness issues in those applications. In this paper, we present a unified framework for a number of foreground segmentation tasks without any task-specific designs. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and high-frequency components. Our method freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters. Despite introducing only a small number of tunable parameters, EVP achieves superior performance than full fine-tuning and other parameter-efficient fine-tuning methods. Experiments in fourteen datasets across five tasks show the proposed method outperforms other task-specific methods while being considerably simple. The proposed method demonstrates the scalability in different architectures, pre-trained weights, and tasks. The code is available at: https://github.com/NiFangBaAGe/Explicit-Visual-Prompt.

Authors:Tiago Barros, Luís Garrote, Martin Aleksandrov, Cristiano Premebida, Urbano J. Nunes

Abstract: Autonomous driving systems often require reliable loop closure detection to guarantee reduced localization drift. Recently, 3D LiDAR-based localization methods have used retrieval-based place recognition to find revisited places efficiently. However, when deployed in challenging real-world scenarios, the place recognition models become more complex, which comes at the cost of high computational demand. This work tackles this problem from an information-retrieval perspective, adopting a first-retrieve-then-re-ranking paradigm, where an initial loop candidate ranking, generated from a 3D place recognition model, is re-ordered by a proposed lightweight transformer-based re-ranking approach (TReR). The proposed approach relies on global descriptors only, being agnostic to the place recognition model. The experimental evaluation, conducted on the KITTI Odometry dataset, where we compared TReR with s.o.t.a. re-ranking approaches such as alphaQE and SGV, indicate the robustness and efficiency when compared to alphaQE while offering a good trade-off between robustness and efficiency when compared to SGV.

Authors:Petros Toupas, Christos-Savvas Bouganis, Dimitrios Tzovaras

Abstract: 3D Convolutional Neural Networks are gaining increasing attention from researchers and practitioners and have found applications in many domains, such as surveillance systems, autonomous vehicles, human monitoring systems, and video retrieval. However, their widespread adoption is hindered by their high computational and memory requirements, especially when resource-constrained systems are targeted. This paper addresses the problem of mapping X3D, a state-of-the-art model in Human Action Recognition that achieves accuracy of 95.5\% in the UCF101 benchmark, onto any FPGA device. The proposed toolflow generates an optimised stream-based hardware system, taking into account the available resources and off-chip memory characteristics of the FPGA device. The generated designs push further the current performance-accuracy pareto front, and enable for the first time the targeting of such complex model architectures for the Human Action Recognition task.

Authors:Ruiyang Li, Fujun Yang, Xianjie Liu, Hongwei Shi

Abstract: Prosthetic Joint Infection (PJI) is a prevalent and severe complication characterized by high diagnostic challenges. Currently, a unified diagnostic standard incorporating both computed tomography (CT) images and numerical text data for PJI remains unestablished, owing to the substantial noise in CT images and the disparity in data volume between CT images and text data. This study introduces a diagnostic method, HGT, based on deep learning and multimodal techniques. It effectively merges features from CT scan images and patients' numerical text data via a Unidirectional Selective Attention (USA) mechanism and a graph convolutional network (GCN)-based feature fusion network. We evaluated the proposed method on a custom-built multimodal PJI dataset, assessing its performance through ablation experiments and interpretability evaluations. Our method achieved an accuracy (ACC) of 91.4\% and an area under the curve (AUC) of 95.9\%, outperforming recent multimodal approaches by 2.9\% in ACC and 2.2\% in AUC, with a parameter count of only 68M. Notably, the interpretability results highlighted our model's strong focus and localization capabilities at lesion sites. This proposed method could provide clinicians with additional diagnostic tools to enhance accuracy and efficiency in clinical practice.

Authors:Cameron Trotter, Filipa Peleja, Dario Dotti, Alberto de Santos

Abstract: There is high demand for online fashion recommender systems that incorporate the needs of the consumer's body shape. As such, we present a methodology to classify human body shape from a single image. This is achieved through the use of instance segmentation and keypoint estimation models, trained only on open-source benchmarking datasets. The system is capable of performing in noisy environments owing to to robust background subtraction. The proposed methodology does not require 3D body recreation as a result of classification based on estimated keypoints, nor requires historical information about a user to operate - calculating all required measurements at the point of use. We evaluate our methodology both qualitatively against existing body shape classifiers and quantitatively against a novel dataset of images, which we provide for use to the community. The resultant body shape classification can be utilised in a variety of downstream tasks, such as input to size and fit recommendation or virtual try-on systems.

Authors:Andreas Petridis, Mirela Popa, Filipa Peleja, Dario Dotti, Alberto de Santos

Abstract: Fashion is one of the largest world's industries and computer vision techniques have been becoming more popular in recent years, in particular, for tasks such as object detection and apparel segmentation. Even with the rapid growth in computer vision solutions, specifically for the fashion industry, many problems are far for being resolved. Therefore, not at all times, adjusting out-of-the-box pre-trained computer vision models will provide the desired solution. In the present paper is proposed a pipeline that takes a noisy image with a person and specifically detects the regions with garments that are bottoms or tops. Our solution implements models that are capable of finding human parts in an image e.g. full-body vs half-body, or no human is found. Then, other models knowing that there's a human and its composition (e.g. not always we have a full-body) finds the bounding boxes/regions of the image that very likely correspond to a bottom or a top. For the creation of bounding boxes/regions task, a benchmark dataset was specifically prepared. The results show that the Mask RCNN solution is robust, and generalized enough to be used and scalable in unseen apparel/fashion data.

Authors:Qian Wang, Biao Zhang, Michael Birsak, Peter Wonka

Abstract: Recent works have explored text-guided image editing using diffusion models and generated edited images based on text prompts. However, the models struggle to accurately locate the regions to be edited and faithfully perform precise edits. In this work, we propose a framework termed InstructEdit that can do fine-grained editing based on user instructions. Our proposed framework has three components: language processor, segmenter, and image editor. The first component, the language processor, processes the user instruction using a large language model. The goal of this processing is to parse the user instruction and output prompts for the segmenter and captions for the image editor. We adopt ChatGPT and optionally BLIP2 for this step. The second component, the segmenter, uses the segmentation prompt provided by the language processor. We employ a state-of-the-art segmentation framework Grounded Segment Anything to automatically generate a high-quality mask based on the segmentation prompt. The third component, the image editor, uses the captions from the language processor and the masks from the segmenter to compute the edited image. We adopt Stable Diffusion and the mask-guided generation from DiffEdit for this purpose. Experiments show that our method outperforms previous editing methods in fine-grained editing applications where the input image contains a complex object or multiple objects. We improve the mask quality over DiffEdit and thus improve the quality of edited images. We also show that our framework can accept multiple forms of user instructions as input. We provide the code at https://github.com/QianWangX/InstructEdit.

Authors:Thomas M. Mercier, Tasmiat Rahman, Amin Sabet

Abstract: This paper proposes an anticipative transformer-based model for short-term solar irradiance forecasting. Given a sequence of sky images, our proposed vision transformer encodes features of consecutive images, feeding into a transformer decoder to predict irradiance values associated with future unseen sky images. We show that our model effectively learns to attend only to relevant features in images in order to forecast irradiance. Moreover, the proposed anticipative transformer captures long-range dependencies between sky images to achieve a forecasting skill of 21.45 % on a 15 minute ahead prediction for a newly introduced dataset of all-sky images when compared to a smart persistence model.

Authors:Haojun Yu, Youcheng Li, QuanLin Wu, Ziwei Zhao, Dengbo Chen, Dong Wang, Liwei Wang

Abstract: During ultrasonic scanning processes, real-time lesion detection can assist radiologists in accurate cancer diagnosis. However, this essential task remains challenging and underexplored. General-purpose real-time object detection models can mistakenly report obvious false positives (FPs) when applied to ultrasound videos, potentially misleading junior radiologists. One key issue is their failure to utilize negative symptoms in previous frames, denoted as negative temporal contexts (NTC). To address this issue, we propose to extract contexts from previous frames, including NTC, with the guidance of inverse optical flow. By aggregating extracted contexts, we endow the model with the ability to suppress FPs by leveraging NTC. We call the resulting model UltraDet. The proposed UltraDet demonstrates significant improvement over previous state-of-the-arts and achieves real-time inference speed. To facilitate future research, we will release the code, checkpoints, and high-quality labels of the CVA-BUS dataset used in our experiments.

Authors:Tao Yang, Yuwang Wang, Cuiling Lan, Yan Lu, Nanning Zheng

Abstract: Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental abilities for humans to support rapid knowledge learning and generalize to new tasks, with which the deep learning models struggle. Towards human-like intelligence, various works on disentangled representation learning have been proposed, and recently some studies on compositional generalization have been presented. However, few works study the relationship between disentanglement and compositional generalization, and the observed results are inconsistent. In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization. This insight also resonates the neuroscience research that the brain encodes information in neuron population activity rather than individual neurons. Motivated by this observation, we further propose a method to reform the scalar-based disentanglement works ($\beta$-TCVAE and FactorVAE) to be vector-based to increase both capabilities. We investigate the impact of the dimensions of vector-based representation and one important question: whether better disentanglement indicates higher compositional generalization. In summary, our study demonstrates that it is possible to achieve both good concept recognition and novel concept composition, contributing an important step towards human-like intelligence.

Authors:Mart Keizer, Zeno Geradts, Meike Kombrink

Abstract: This research evaluates a convolutional neural network (CNN) based approach to forensic video steganalysis. A video steganography dataset is created to train a CNN to conduct forensic steganalysis in the spatial domain. We use a noise residual convolutional neural network to detect embedded secrets since a steganographic embedding process will always result in the modification of pixel values in video frames. Experimental results show that the CNN-based approach can be an effective method for forensic video steganalysis and can reach a detection rate of 99.96%. Keywords: Forensic, Steganalysis, Deep Steganography, MSU StegoVideo, Convolutional Neural Networks

Authors:Feipeng Ma, Yizhou Zhou, Fengyun Rao, Yueyi Zhang, Xiaoyan Sun

Abstract: Text-only Image Captioning (TIC) is an approach that aims to construct a model solely based on text that can accurately describe images. Recently, diffusion models have demonstrated remarkable capabilities in generating high-quality images that are semantically coherent with given texts. This presents an opportunity to generate synthetic training images for TIC. However, we have identified a challenge that the images generated from simple descriptions typically exhibit a single perspective with one or limited contexts, which is not aligned with the complexity of real-world scenes in the image domain. In this paper, we propose a novel framework that addresses this issue by introducing multi-context data generation. Starting with an initial text corpus, our framework employs a large language model to select multiple sentences that describe the same scene from various perspectives. These sentences are then summarized into a single sentence with multiple contexts. We generate simple images using the straightforward sentences and complex images using the summarized sentences through diffusion models. Finally, we train the model exclusively using the synthetic image-text pairs obtained from this process. Experimental results demonstrate that our proposed framework effectively tackles the central challenge we have identified, achieving the state-of-the-art performance on popular datasets such as MSCOCO, Flickr30k, and SS1M.

Authors:Tao Feng, Jie Zhang, Peizheng Wang, Zhijie Wang

Abstract: The expenses involved in training state-of-the-art deep hashing retrieval models have witnessed an increase due to the adoption of more sophisticated models and large-scale datasets. Dataset Distillation (DD) or Dataset Condensation(DC) focuses on generating smaller synthetic dataset that retains the original information. Nevertheless, existing DD methods face challenges in maintaining a trade-off between accuracy and efficiency. And the state-of-the-art dataset distillation methods can not expand to all deep hashing retrieval methods. In this paper, we propose an efficient condensation framework that addresses these limitations by matching the feature-embedding between synthetic set and real set. Furthermore, we enhance the diversity of features by incorporating the strategies of early-stage augmented models and multi-formation. Extensive experiments provide compelling evidence of the remarkable superiority of our approach, both in terms of performance and efficiency, compared to state-of-the-art baseline methods.

Authors:Yarden Tzach, Yuval Meir, Ofek Tevet, Ronit D. Gross, Shiri Hodassman, Roni Vardi, Ido Kanter

Abstract: Deep architectures consist of tens or hundreds of convolutional layers (CLs) that terminate with a few fully connected (FC) layers and an output layer representing the possible labels of a complex classification task. According to the existing deep learning (DL) rationale, the first CL reveals localized features from the raw data, whereas the subsequent layers progressively extract higher-level features required for refined classification. This article presents an efficient three-phase procedure for quantifying the mechanism underlying successful DL. First, a deep architecture is trained to maximize the success rate (SR). Next, the weights of the first several CLs are fixed and only the concatenated new FC layer connected to the output is trained, resulting in SRs that progress with the layers. Finally, the trained FC weights are silenced, except for those emerging from a single filter, enabling the quantification of the functionality of this filter using a correlation matrix between input labels and averaged output fields, hence a well-defined set of quantifiable features is obtained. Each filter essentially selects a single output label independent of the input label, which seems to prevent high SRs; however, it counterintuitively identifies a small subset of possible output labels. This feature is an essential part of the underlying DL mechanism and is progressively sharpened with layers, resulting in enhanced signal-to-noise ratios and SRs. Quantitatively, this mechanism is exemplified by the VGG-16, VGG-6, and AVGG-16. The proposed mechanism underlying DL provides an accurate tool for identifying each filter's quality and is expected to direct additional procedures to improve the SR, computational complexity, and latency of DL.

Authors:Adrian Azzarelli, Nantheera Anantrasirichai, David R Bull

Abstract: Neural Radiance Field (NeRF) research has attracted significant attention recently, with 3D modelling, virtual/augmented reality, and visual effects driving its application. While current NeRF implementations can produce high quality visual results, there is a conspicuous lack of reliable methods for evaluating them. Conventional image quality assessment methods and analytical metrics (e.g. PSNR, SSIM, LPIPS etc.) only provide approximate indicators of performance since they generalise the ability of the entire NeRF pipeline. Hence, in this paper, we propose a new test framework which isolates the neural rendering network from the NeRF pipeline and then performs a parametric evaluation by training and evaluating the NeRF on an explicit radiance field representation. We also introduce a configurable approach for generating representations specifically for evaluation purposes. This employs ray-casting to transform mesh models into explicit NeRF samples, as well as to "shade" these representations. Combining these two approaches, we demonstrate how different "tasks" (scenes with different visual effects or learning strategies) and types of networks (NeRFs and depth-wise implicit neural representations (INRs)) can be evaluated within this framework. Additionally, we propose a novel metric to measure task complexity of the framework which accounts for the visual parameters and the distribution of the spatial data. Our approach offers the potential to create a comparative objective evaluation framework for NeRF methods.

Authors:Zhiying Jiang, Risheng Liu, Shuzhou Yang, Zengxi Zhang, Xin Fan

Abstract: Rain streaks significantly decrease the visibility of captured images and are also a stumbling block that restricts the performance of subsequent computer vision applications. The existing deep learning-based image deraining methods employ manually crafted networks and learn a straightforward projection from rainy images to clear images. In pursuit of better deraining performance, they focus on elaborating a more complicated architecture rather than exploiting the intrinsic properties of the positive and negative information. In this paper, we propose a contrastive learning-based image deraining method that investigates the correlation between rainy and clear images and leverages a contrastive prior to optimize the mutual information of the rainy and restored counterparts. Given the complex and varied real-world rain patterns, we develop a recursive mechanism. It involves multi-scale feature extraction and dynamic cross-level information recruitment modules. The former advances the portrayal of diverse rain patterns more precisely, while the latter can selectively compensate high-level features for shallow-level information. We term the proposed recursive dynamic multi-scale network with a contrastive prior, RDMC. Extensive experiments on synthetic benchmarks and real-world images demonstrate that the proposed RDMC delivers strong performance on the depiction of rain streaks and outperforms the state-of-the-art methods. Moreover, a practical evaluation of object detection and semantic segmentation shows the effectiveness of the proposed method.

Authors:Ruofan Zhang, Jinjin Gu, Haoyu Chen, Chao Dong, Yulun Zhang, Wenming Yang

Abstract: Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range degradations to enhance generalization, a decline in accuracy is inevitable. However, since the degradation in a certain real-world applications typically exhibits a limited variation range, it becomes feasible to strike a trade-off between generalization performance and testing accuracy within this scope. In this work, we introduce a novel approach to craft training degradation distributions using a small set of reference images. Our strategy is founded upon the binned representation of the degradation space and the Fr\'echet distance between degradation distributions. Our results indicate that the proposed technique significantly improves the performance of test images while preserving generalization capabilities in real-world applications.

Authors:Jialong Wu, Haoyu Ma, Chaoyi Deng, Mingsheng Long

Abstract: Unsupervised pre-training methods utilizing large and diverse datasets have achieved tremendous success across a range of domains. Recent work has investigated such unsupervised pre-training methods for model-based reinforcement learning (MBRL) but is limited to domain-specific or simulated data. In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of downstream visual control tasks. However, in-the-wild videos are complicated with various contextual factors, such as intricate backgrounds and textured appearance, which precludes a world model from extracting shared world knowledge to generalize better. To tackle this issue, we introduce Contextualized World Models (ContextWM) that explicitly model both the context and dynamics to overcome the complexity and diversity of in-the-wild videos and facilitate knowledge transfer between distinct scenes. Specifically, a contextualized extension of the latent dynamics model is elaborately realized by incorporating a context encoder to retain contextual information and empower the image decoder, which allows the latent dynamics model to concentrate on essential temporal variations. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample-efficiency of MBRL in various domains, including robotic manipulation, locomotion, and autonomous driving.

Authors:Reza Dadfar, Sanaz Sabzevari, Mårten Björkman, Danica Kragic

Abstract: Language-based fashion image editing allows users to try out variations of desired garments through provided text prompts. Inspired by research on manipulating latent representations in StyleCLIP and HairCLIP, we focus on these latent spaces for editing fashion items of full-body human datasets. Currently, there is a gap in handling fashion image editing due to the complexity of garment shapes and textures and the diversity of human poses. In this paper, we propose an editing optimizer scheme method called Text-Driven Garment Editing Mapper (TD-GEM), aiming to edit fashion items in a disentangled way. To this end, we initially obtain a latent representation of an image through generative adversarial network inversions such as Encoder for Editing (e4e) or Pivotal Tuning Inversion (PTI) for more accurate results. An optimization-based Contrasive Language-Image Pre-training (CLIP) is then utilized to guide the latent representation of a fashion image in the direction of a target attribute expressed in terms of a text prompt. Our TD-GEM manipulates the image accurately according to the target attribute, while other parts of the image are kept untouched. In the experiments, we evaluate TD-GEM on two different attributes (i.e., "color" and "sleeve length"), which effectively generates realistic images compared to the recent manipulation schemes.

Authors:Sihan Chen, Handong Li, Qunbo Wang, Zijia Zhao, Mingzhen Sun, Xinxin Zhu, Jing Liu

Abstract: Vision and text have been fully explored in contemporary video-text foundational models, while other modalities such as audio and subtitles in videos have not received sufficient attention. In this paper, we resort to establish connections between multi-modality video tracks, including Vision, Audio, and Subtitle, and Text by exploring an automatically generated large-scale omni-modality video caption dataset called VAST-27M. Specifically, we first collect 27 million open-domain video clips and separately train a vision and an audio captioner to generate vision and audio captions. Then, we employ an off-the-shelf Large Language Model (LLM) to integrate the generated captions, together with subtitles and instructional prompts into omni-modality captions. Based on the proposed VAST-27M dataset, we train an omni-modality video-text foundational model named VAST, which can perceive and process vision, audio, and subtitle modalities from video, and better support various tasks including vision-text, audio-text, and multi-modal video-text tasks (retrieval, captioning and QA). Extensive experiments have been conducted to demonstrate the effectiveness of our proposed VAST-27M corpus and VAST foundation model. VAST achieves 22 new state-of-the-art results on various cross-modality benchmarks. Code, model and dataset will be released at https://github.com/TXH-mercury/VAST.

Authors:Steven Tel, Zongwei Wu, Yulun Zhang, Barthélémy Heyrman, Cédric Demonceaux, Radu Timofte, Dominique Ginhac

Abstract: High dynamic range (HDR) imaging aims to retrieve information from multiple low-dynamic range inputs to generate realistic output. The essence is to leverage the contextual information, including both dynamic and static semantics, for better image generation. Existing methods often focus on the spatial misalignment across input frames caused by the foreground and/or camera motion. However, there is no research on jointly leveraging the dynamic and static context in a simultaneous manner. To delve into this problem, we propose a novel alignment-free network with a Semantics Consistent Transformer (SCTNet) with both spatial and channel attention modules in the network. The spatial attention aims to deal with the intra-image correlation to model the dynamic motion, while the channel attention enables the inter-image intertwining to enhance the semantic consistency across frames. Aside from this, we introduce a novel realistic HDR dataset with more variations in foreground objects, environmental factors, and larger motions. Extensive comparisons on both conventional datasets and ours validate the effectiveness of our method, achieving the best trade-off on the performance and the computational cost.

Authors:Yu Wang, Pengchong Qiao, Chang Liu, Guoli Song, Xiawu Zheng, Jie Chen

Abstract: Recent advances in robust semi-supervised learning (SSL) typically filter out-of-distribution (OOD) information at the sample level. We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field. In this paper, we take an initial step to explore and propose a unified framework termed OOD Semantic Pruning (OSP), which aims at pruning OOD semantics out from in-distribution (ID) features. Specifically, (i) we propose an aliasing OOD matching module to pair each ID sample with an OOD sample with semantic overlap. (ii) We design a soft orthogonality regularization, which first transforms each ID feature by suppressing its semantic component that is collinear with paired OOD sample. It then forces the predictions before and after soft orthogonality decomposition to be consistent. Being practically simple, our method shows a strong performance in OOD detection and ID classification on challenging benchmarks. In particular, OSP surpasses the previous state-of-the-art by 13.7% on accuracy for ID classification and 5.9% on AUROC for OOD detection on TinyImageNet dataset. The source codes are publicly available at https://github.com/rain305f/OSP.

Authors:Lingzhi Li, Zhongshu Wang, Zhen Shen, Li Shen, Ping Tan

Abstract: Reconstructing neural radiance fields with explicit volumetric representations, demonstrated by Plenoxels, has shown remarkable advantages on training and rendering efficiency, while grid-based representations typically induce considerable overhead for storage and transmission. In this work, we present a simple and effective framework for pursuing compact radiance fields from the perspective of compression methodology. By exploiting intrinsic properties exhibiting in grid models, a non-uniform compression stem is developed to significantly reduce model complexity and a novel parameterized module, named Neural Codebook, is introduced for better encoding high-frequency details specific to per-scene models via a fast optimization. Our approach can achieve over 40 $\times$ reduction on grid model storage with competitive rendering quality. In addition, the method can achieve real-time rendering speed with 180 fps, realizing significant advantage on storage cost compared to real-time rendering methods.

Authors:Sanghyuk Chun

Abstract: Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Probabilistic Cross-Modal Embeddings (named PCME++) by introducing a new probabilistic distance with a closed-form solution. In addition, two optimization techniques are proposed to enhance PCME++ further; first, the incorporation of pseudo-positives to prevent the loss saturation problem under massive false negatives; second, mixed sample data augmentation for probabilistic matching. Experimental results on MS-COCO Caption and two extended benchmarks, CxC and ECCV Caption, demonstrate the effectiveness of PCME++ compared to state-of-the-art ITM methods. The robustness of PCME++ is also evaluated under noisy image-text correspondences. In addition, the potential applicability of PCME++ in automatic prompt tuning for zero-shot classification is shown. The code is available at https://naver-ai.github.io/pcmepp/.

Authors:Daniel Coelho, Miguel Oliveira, Vitor Santos

Abstract: Current approaches of Reinforcement Learning (RL) applied in urban Autonomous Driving (AD) focus on decoupling the perception training from the driving policy training. The main reason is to avoid training a convolution encoder alongside a policy network, which is known to have issues related to sample efficiency, degenerated feature representations, and catastrophic self-overfitting. However, this paradigm can lead to representations of the environment that are not aligned with the downstream task, which may result in suboptimal performances. To address this limitation, this paper proposes RLAD, the first Reinforcement Learning from Pixels (RLfP) method applied in the urban AD domain. We propose several techniques to enhance the performance of an RLfP algorithm in this domain, including: i) an image encoder that leverages both image augmentations and Adaptive Local Signal Mixing (A-LIX) layers; ii) WayConv1D, which is a waypoint encoder that harnesses the 2D geometrical information of the waypoints using 1D convolutions; and iii) an auxiliary loss to increase the significance of the traffic lights in the latent representation of the environment. Experimental results show that RLAD significantly outperforms all state-of-the-art RLfP methods on the NoCrash benchmark. We also present an infraction analysis on the NoCrash-regular benchmark, which indicates that RLAD performs better than all other methods in terms of both collision rate and red light infractions.

Authors:Yael Vinker, Andrey Voynov, Daniel Cohen-Or, Ariel Shamir

Abstract: A creative idea is often born from transforming, combining, and modifying ideas from existing visual examples capturing various concepts. However, one cannot simply copy the concept as a whole, and inspiration is achieved by examining certain aspects of the concept. Hence, it is often necessary to separate a concept into different aspects to provide new perspectives. In this paper, we propose a method to decompose a visual concept, represented as a set of images, into different visual aspects encoded in a hierarchical tree structure. We utilize large vision-language models and their rich latent space for concept decomposition and generation. Each node in the tree represents a sub-concept using a learned vector embedding injected into the latent space of a pretrained text-to-image model. We use a set of regularizations to guide the optimization of the embedding vectors encoded in the nodes to follow the hierarchical structure of the tree. Our method allows to explore and discover new concepts derived from the original one. The tree provides the possibility of endless visual sampling at each node, allowing the user to explore the hidden sub-concepts of the object of interest. The learned aspects in each node can be combined within and across trees to create new visual ideas, and can be used in natural language sentences to apply such aspects to new designs.

Authors:Roman Kessler, Kiran Raja, Juan Tapia, Christoph Busch

Abstract: Face Morphing Attacks pose a threat to the security of identity documents, especially with respect to a subsequent access control process, because it enables both individuals involved to exploit the same document. In this study, face embeddings serve two purposes: pre-selecting images for large-scale Morphing Attack generation and detecting potential Morphing Attacks. We build upon previous embedding studies in both use cases using the MagFace model. For the first objective, we employ an pre-selection algorithm that pairs individuals based on face embedding similarity. We quantify the attack potential of differently morphed face images to compare the usability of pre-selection in automatically generating numerous successful Morphing Attacks. Regarding the second objective, we compare embeddings from two state-of-the-art face recognition systems in terms of their ability to detect Morphing Attacks. Our findings demonstrate that ArcFace and MagFace provide valuable face embeddings for image pre-selection. Both open-source and COTS face recognition systems are susceptible to generated attacks, particularly when pre-selection is based on embeddings rather than random pairing which was only constrained by soft biometrics. More accurate face recognition systems exhibit greater vulnerability to attacks, with COTS systems being the most susceptible. Additionally, MagFace embeddings serve as a robust alternative for detecting morphed face images compared to the previously used ArcFace embeddings. The results endorse the advantages of face embeddings in more effective image pre-selection for face morphing and accurate detection of morphed face images. This is supported by extensive analysis of various designed attacks. The MagFace model proves to be a powerful alternative to the commonly used ArcFace model for both objectives, pre-selection and attack detection.

Authors:Bin Wang, Hongyi Pan, Armstrong Aboah, Zheyuan Zhang, Ahmet Cetin, Drew Torigian, Baris Turkbey, Elizabeth Krupinski, Jayaram Udupa, Ulas Bagci

Abstract: The application of eye-tracking techniques in medical image analysis has become increasingly popular in recent years. It collects the visual search patterns of the domain experts, containing much important information about health and disease. Therefore, how to efficiently integrate radiologists' gaze patterns into the diagnostic analysis turns into a critical question. Existing works usually transform gaze information into visual attention maps (VAMs) to supervise the learning process. However, this time-consuming procedure makes it difficult to develop end-to-end algorithms. In this work, we propose a novel gaze-guided graph neural network (GNN), GazeGNN, to perform disease classification from medical scans. In GazeGNN, we create a unified representation graph that models both the image and gaze pattern information. Hence, the eye-gaze information is directly utilized without being converted into VAMs. With this benefit, we develop a real-time, real-world, end-to-end disease classification algorithm for the first time and avoid the noise and time consumption introduced during the VAM preparation. To our best knowledge, GazeGNN is the first work that adopts GNN to integrate image and eye-gaze data. Our experiments on the public chest X-ray dataset show that our proposed method exhibits the best classification performance compared to existing methods.

Authors:Yuan Gong, Youxin Pang, Xiaodong Cun, Menghan Xia, Yingqing He, Haoxin Chen, Longyue Wang, Yong Zhang, Xintao Wang, Ying Shan, Yujiu Yang

Abstract: Accurate Story visualization requires several necessary elements, such as identity consistency across frames, the alignment between plain text and visual content, and a reasonable layout of objects in images. Most previous works endeavor to meet these requirements by fitting a text-to-image (T2I) model on a set of videos in the same style and with the same characters, e.g., the FlintstonesSV dataset. However, the learned T2I models typically struggle to adapt to new characters, scenes, and styles, and often lack the flexibility to revise the layout of the synthesized images. This paper proposes a system for generic interactive story visualization, capable of handling multiple novel characters and supporting the editing of layout and local structure. It is developed by leveraging the prior knowledge of large language and T2I models, trained on massive corpora. The system comprises four interconnected components: story-to-prompt generation (S2P), text-to-layout generation (T2L), controllable text-to-image generation (C-T2I), and image-to-video animation (I2V). First, the S2P module converts concise story information into detailed prompts required for subsequent stages. Next, T2L generates diverse and reasonable layouts based on the prompts, offering users the ability to adjust and refine the layout to their preference. The core component, C-T2I, enables the creation of images guided by layouts, sketches, and actor-specific identifiers to maintain consistency and detail across visualizations. Finally, I2V enriches the visualization process by animating the generated images. Extensive experiments and a user study are conducted to validate the effectiveness and flexibility of interactive editing of the proposed system.

Authors:Yukang Yang, Dongnan Gui, Yuhui Yuan, Haisong Ding, Han Hu, Kai Chen

Abstract: Recently, there has been a growing interest in developing diffusion-based text-to-image generative models capable of generating coherent and well-formed visual text. In this paper, we propose a novel and efficient approach called GlyphControl to address this task. Unlike existing methods that rely on character-aware text encoders like ByT5 and require retraining of text-to-image models, our approach leverages additional glyph conditional information to enhance the performance of the off-the-shelf Stable-Diffusion model in generating accurate visual text. By incorporating glyph instructions, users can customize the content, location, and size of the generated text according to their specific requirements. To facilitate further research in visual text generation, we construct a training benchmark dataset called LAION-Glyph. We evaluate the effectiveness of our approach by measuring OCR-based metrics and CLIP scores of the generated visual text. Our empirical evaluations demonstrate that GlyphControl outperforms the recent DeepFloyd IF approach in terms of OCR accuracy and CLIP scores, highlighting the efficacy of our method.

Authors:Daniel Coelho, Miguel Oliveira, Paulo Dias

Abstract: Collecting real-world data is often considered the bottleneck of Artificial Intelligence, stalling the research progress in several fields, one of which is camera localization. End-to-end camera localization methods are still outperformed by traditional methods, and we argue that the inconsistencies associated with the data collection techniques are restraining the potential of end-to-end methods. Inspired by the recent data-centric paradigm, we propose a framework that synthesizes large localization datasets based on realistic 3D reconstructions of the real world. Our framework, termed Synfeal: Synthetic from Real, is an open-source, data-driven simulator that synthesizes RGB images by moving a virtual camera through a realistic 3D textured mesh, while collecting the corresponding ground-truth camera poses. The results validate that the training of camera localization algorithms on datasets generated by Synfeal leads to better results when compared to datasets generated by state-of-the-art methods. Using Synfeal, we conducted the first analysis of the relationship between the size of the dataset and the performance of camera localization algorithms. Results show that the performance significantly increases with the dataset size. Our results also suggest that when a large localization dataset with high quality is available, training from scratch leads to better performances. Synfeal is publicly available at https://github.com/DanielCoelho112/synfeal.

Authors:Fu-Yun Wang, Wenshuo Chen, Guanglu Song, Han-Jia Ye, Yu Liu, Hongsheng Li

Abstract: Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and editing. This study explores the potential of extending the text-driven ability to the generation and editing of multi-text conditioned long videos. Current methodologies for video generation and editing, while innovative, are often confined to extremely short videos (typically less than 24 frames) and are limited to a single text condition. These constraints significantly limit their applications given that real-world videos usually consist of multiple segments, each bearing different semantic information. To address this challenge, we introduce a novel paradigm dubbed as Gen-L-Video, capable of extending off-the-shelf short video diffusion models for generating and editing videos comprising hundreds of frames with diverse semantic segments without introducing additional training, all while preserving content consistency. We have implemented three mainstream text-driven video generation and editing methodologies and extended them to accommodate longer videos imbued with a variety of semantic segments with our proposed paradigm. Our experimental outcomes reveal that our approach significantly broadens the generative and editing capabilities of video diffusion models, offering new possibilities for future research and applications. The code is available at https://github.com/G-U-N/Gen-L-Video.

Authors:Nikolas Lamb, Sean Banerjee, Natasha Kholgade Banerjee

Abstract: We present Pix2Repair, an automated shape repair approach that generates restoration shapes from images to repair fractured objects. Prior repair approaches require a high-resolution watertight 3D mesh of the fractured object as input. Input 3D meshes must be obtained using expensive 3D scanners, and scanned meshes require manual cleanup, limiting accessibility and scalability. Pix2Repair takes an image of the fractured object as input and automatically generates a 3D printable restoration shape. We contribute a novel shape function that deconstructs a latent code representing the fractured object into a complete shape and a break surface. We show restorations for synthetic fractures from the Geometric Breaks and Breaking Bad datasets, and cultural heritage objects from the QP dataset, and for real fractures from the Fantastic Breaks dataset. We overcome challenges in restoring axially symmetric objects by predicting view-centered restorations. Our approach outperforms shape completion approaches adapted for shape repair in terms of chamfer distance, earth mover's distance, normal consistency, and percent restorations generated.

Authors:Paul S. Scotti, Atmadeep Banerjee, Jimmie Goode, Stepan Shabalin, Alex Nguyen, Ethan Cohen, Aidan J. Dempster, Nathalie Verlinde, Elad Yundler, David Weisberg, Kenneth A. Norman, Tanishq Mathew Abraham

Abstract: We present MindEye, a novel fMRI-to-image approach to retrieve and reconstruct viewed images from brain activity. Our model comprises two parallel submodules that are specialized for retrieval (using contrastive learning) and reconstruction (using a diffusion prior). MindEye can map fMRI brain activity to any high dimensional multimodal latent space, like CLIP image space, enabling image reconstruction using generative models that accept embeddings from this latent space. We comprehensively compare our approach with other existing methods, using both qualitative side-by-side comparisons and quantitative evaluations, and show that MindEye achieves state-of-the-art performance in both reconstruction and retrieval tasks. In particular, MindEye can retrieve the exact original image even among highly similar candidates indicating that its brain embeddings retain fine-grained image-specific information. This allows us to accurately retrieve images even from large-scale databases like LAION-5B. We demonstrate through ablations that MindEye's performance improvements over previous methods result from specialized submodules for retrieval and reconstruction, improved training techniques, and training models with orders of magnitude more parameters. Furthermore, we show that MindEye can better preserve low-level image features in the reconstructions by using img2img, with outputs from a separate autoencoder. All code is available on GitHub.

Authors:Achraf Ben-Hamadou, Oussama Smaoui, Ahmed Rekik, Sergi Pujades, Edmond Boyer, Hoyeon Lim, Minchang Kim, Minkyung Lee, Minyoung Chung, Yeong-Gil Shin, Mathieu Leclercq, Lucia Cevidanes, Juan Carlos Prieto, Shaojie Zhuang, Guangshun Wei, Zhiming Cui, Yuanfeng Zhou, Tudor Dascalu, Bulat Ibragimov, Tae-Hoon Yong, Hong-Gi Ahn, Wan Kim, Jae-Hwan Han, Byungsun Choi, Niels van Nistelrooij, Steven Kempers, Shankeeth Vinayahalingam, Julien Strippoli, Aurélien Thollot, Hugo Setbon, Cyril Trosset, Edouard Ladroit

Abstract: Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due to variations in dental anatomy, imaging protocols, and limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg'22 challenge was organized in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2022, with a call for algorithms tackling teeth localization, segmentation, and labeling from intraoral 3D scans. A dataset comprising a total of 1800 scans from 900 patients was prepared, and each tooth was individually annotated by a human-machine hybrid algorithm. A total of 6 algorithms were evaluated on this dataset. In this study, we present the evaluation results of the 3DTeethSeg'22 challenge. The 3DTeethSeg'22 challenge code can be accessed at: https://github.com/abenhamadou/3DTeethSeg22_challenge

Authors:Yuhang Zang, Wei Li, Jun Han, Kaiyang Zhou, Chen Change Loy

Abstract: Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this limitation by introducing a novel research problem of contextual object detection -- understanding visible objects within different human-AI interactive contexts. Three representative scenarios are investigated, including the language cloze test, visual captioning, and question answering. Moreover, we present ContextDET, a unified multimodal model that is capable of end-to-end differentiable modeling of visual-language contexts, so as to locate, identify, and associate visual objects with language inputs for human-AI interaction. Our ContextDET involves three key submodels: (i) a visual encoder for extracting visual representations, (ii) a pre-trained LLM for multimodal context decoding, and (iii) a visual decoder for predicting bounding boxes given contextual object words. The new generate-then-detect framework enables us to detect object words within human vocabulary. Extensive experiments show the advantages of ContextDET on our proposed CODE benchmark, open-vocabulary detection, and referring image segmentation. Github: https://github.com/yuhangzang/ContextDET.

Authors:Jing Gu, Yilin Wang, Nanxuan Zhao, Tsu-Jui Fu, Wei Xiong, Qing Liu, Zhifei Zhang, He Zhang, Jianming Zhang, HyunJoon Jung, Xin Eric Wang

Abstract: In an era where images and visual content dominate our digital landscape, the ability to manipulate and personalize these images has become a necessity. Envision seamlessly substituting a tabby cat lounging on a sunlit window sill in a photograph with your own playful puppy, all while preserving the original charm and composition of the image. We present Photoswap, a novel approach that enables this immersive image editing experience through personalized subject swapping in existing images. Photoswap first learns the visual concept of the subject from reference images and then swaps it into the target image using pre-trained diffusion models in a training-free manner. We establish that a well-conceptualized visual subject can be seamlessly transferred to any image with appropriate self-attention and cross-attention manipulation, maintaining the pose of the swapped subject and the overall coherence of the image. Comprehensive experiments underscore the efficacy and controllability of Photoswap in personalized subject swapping. Furthermore, Photoswap significantly outperforms baseline methods in human ratings across subject swapping, background preservation, and overall quality, revealing its vast application potential, from entertainment to professional editing.

Authors:M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Mateusz Kozinski, Horst Possegger, Rogerio Feris, Horst Bischof

Abstract: Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple language prompts. However, despite these great advances, the performance of these zeroshot classifiers still falls short of the results of dedicated (closed category set) classifiers trained with supervised fine tuning. In this paper we show, for the first time, how to reduce this gap without any labels and without any paired VL data, using an unlabeled image collection and a set of texts auto-generated using a Large Language Model (LLM) describing the categories of interest and effectively substituting labeled visual instances of those categories. Using our label-free approach, we are able to attain significant performance improvements over the zero-shot performance of the base VL model and other contemporary methods and baselines on a wide variety of datasets, demonstrating absolute improvement of up to 11.7% (3.8% on average) in the label-free setting. Moreover, despite our approach being label-free, we observe 1.3% average gains over leading few-shot prompting baselines that do use 5-shot supervision.

Authors:Yuchao Gu, Xintao Wang, Jay Zhangjie Wu, Yujun Shi, Yunpeng Chen, Zihan Fan, Wuyou Xiao, Rui Zhao, Shuning Chang, Weijia Wu, Yixiao Ge, Ying Shan, Mike Zheng Shou

Abstract: Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the utilization of multiple concept LoRAs to jointly support multiple customized concepts presents a challenge. We refer to this scenario as decentralized multi-concept customization, which involves single-client concept tuning and center-node concept fusion. In this paper, we propose a new framework called Mix-of-Show that addresses the challenges of decentralized multi-concept customization, including concept conflicts resulting from existing single-client LoRA tuning and identity loss during model fusion. Mix-of-Show adopts an embedding-decomposed LoRA (ED-LoRA) for single-client tuning and gradient fusion for the center node to preserve the in-domain essence of single concepts and support theoretically limitless concept fusion. Additionally, we introduce regionally controllable sampling, which extends spatially controllable sampling (e.g., ControlNet and T2I-Adaptor) to address attribute binding and missing object problems in multi-concept sampling. Extensive experiments demonstrate that Mix-of-Show is capable of composing multiple customized concepts with high fidelity, including characters, objects, and scenes.

Authors:Zeyue Xue, Guanglu Song, Qiushan Guo, Boxiao Liu, Zhuofan Zong, Yu Liu, Ping Luo

Abstract: Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a "painter" for depicting a particular textual concept onto a specified image region at a diffusion timestep. Comprehensive experiments reveal that RAPHAEL outperforms recent cutting-edge models, such as Stable Diffusion, ERNIE-ViLG 2.0, DeepFloyd, and DALL-E 2, in terms of both image quality and aesthetic appeal. Firstly, RAPHAEL exhibits superior performance in switching images across diverse styles, such as Japanese comics, realism, cyberpunk, and ink illustration. Secondly, a single model with three billion parameters, trained on 1,000 A100 GPUs for two months, achieves a state-of-the-art zero-shot FID score of 6.61 on the COCO dataset. Furthermore, RAPHAEL significantly surpasses its counterparts in human evaluation on the ViLG-300 benchmark. We believe that RAPHAEL holds the potential to propel the frontiers of image generation research in both academia and industry, paving the way for future breakthroughs in this rapidly evolving field. More details can be found on a project webpage: https://raphael-painter.github.io/.

Authors:Supriya Gadi Patil, Angel X. Chang, Manolis Savva

Abstract: This paper analyzes the robustness of recent 3D shape descriptors to SO(3) rotations, something that is fundamental to shape modeling. Specifically, we formulate the task of rotated 3D object instance detection. To do so, we consider a database of 3D indoor scenes, where objects occur in different orientations. We benchmark different methods for feature extraction and classification in the context of this task. We systematically contrast different choices in a variety of experimental settings investigating the impact on the performance of different rotation distributions, different degrees of partial observations on the object, and the different levels of difficulty of negative pairs. Our study, on a synthetic dataset of 3D scenes where objects instances occur in different orientations, reveals that deep learning-based rotation invariant methods are effective for relatively easy settings with easy-to-distinguish pairs. However, their performance decreases significantly when the difference in rotations on the input pair is large, or when the degree of observation of input objects is reduced, or the difficulty level of input pair is increased. Finally, we connect feature encodings designed for rotation-invariant methods to 3D geometry that enable them to acquire the property of rotation invariance.

Authors:Xi Chen, Josip Djolonga, Piotr Padlewski, Basil Mustafa, Soravit Changpinyo, Jialin Wu, Carlos Riquelme Ruiz, Sebastian Goodman, Xiao Wang, Yi Tay, Siamak Shakeri, Mostafa Dehghani, Daniel Salz, Mario Lucic, Michael Tschannen, Arsha Nagrani, Hexiang Hu, Mandar Joshi, Bo Pang, Ceslee Montgomery, Paulina Pietrzyk, Marvin Ritter, AJ Piergiovanni, Matthias Minderer, Filip Pavetic, Austin Waters, Gang Li, Ibrahim Alabdulmohsin, Lucas Beyer, Julien Amelot, Kenton Lee, Andreas Peter Steiner, Yang Li, Daniel Keysers, Anurag Arnab, Yuanzhong Xu, Keran Rong, Alexander Kolesnikov, Mojtaba Seyedhosseini, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut

Abstract: We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

Authors:Tianjun Zhang, Yi Zhang, Vibhav Vineet, Neel Joshi, Xin Wang

Abstract: Current text-to-image generation models often struggle to follow textual instructions, especially the ones requiring spatial reasoning. On the other hand, Large Language Models (LLMs), such as GPT-4, have shown remarkable precision in generating code snippets for sketching out text inputs graphically, e.g., via TikZ. In this work, we introduce Control-GPT to guide the diffusion-based text-to-image pipelines with programmatic sketches generated by GPT-4, enhancing their abilities for instruction following. Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e.g., ControlNet) to generate photo-realistic images. One major challenge to training our pipeline is the lack of a dataset containing aligned text, images, and sketches. We address the issue by converting instance masks in existing datasets into polygons to mimic the sketches used at test time. As a result, Control-GPT greatly boosts the controllability of image generation. It establishes a new state-of-art on the spatial arrangement and object positioning generation and enhances users' control of object positions, sizes, etc., nearly doubling the accuracy of prior models. Our work, as a first attempt, shows the potential for employing LLMs to enhance the performance in computer vision tasks.

Authors:Dingdong Yang, Yizhi Wang, Ali Mahdavi-Amiri, Hao Zhang

Abstract: We present BRIGHT, a bi-levelfeature representation for an imagecollection, consisting of a per-image latent space on top of a multi-scale feature grid space. Our representation is learned by an autoencoder to encode images intocontinuouskey codes, which are used to retrieve features fromgroups of multi-resolution hashtables. Our key codes and hash tables are trained together continuously with well-defined gradient flows, leading to high usage of the hash table entries and improved generative modeling compared to discrete Vector Quantization (VQ). Differently from existing continuous representations such as KL-regularized latent codes, our key codes are strictly bounded in scale and variance. Overall, feature encoding by BRIGHT is compact, efficient to train, and enables generative modeling over the image codes using state-of-the-art generators such as latent diffusion models(LDMs). Experimental results show that our method achieves comparable recon-struction results to VQ methods while having a smaller and more efficient decoder network. By applying LDM over our key code space, we achieve state-of-the-art performance on image synthesis on the LSUN-Church and human-face datasets.

Authors:Ali Zia, Renuka Sharma, Reza Arablouei, Greg Bishop-Hurley, Jody McNally, Neil Bagnall, Vivien Rolland, Brano Kusy, Lars Petersson, Aaron Ingham

Abstract: Existing image/video datasets for cattle behavior recognition are mostly small, lack well-defined labels, or are collected in unrealistic controlled environments. This limits the utility of machine learning (ML) models learned from them. Therefore, we introduce a new dataset, called Cattle Visual Behaviors (CVB), that consists of 502 video clips, each fifteen seconds long, captured in natural lighting conditions, and annotated with eleven visually perceptible behaviors of grazing cattle. We use the Computer Vision Annotation Tool (CVAT) to collect our annotations. To make the procedure more efficient, we perform an initial detection and tracking of cattle in the videos using appropriate pre-trained models. The results are corrected by domain experts along with cattle behavior labeling in CVAT. The pre-hoc detection and tracking step significantly reduces the manual annotation time and effort. Moreover, we convert CVB to the atomic visual action (AVA) format and train and evaluate the popular SlowFast action recognition model on it. The associated preliminary results confirm that we can localize the cattle and recognize their frequently occurring behaviors with confidence. By creating and sharing CVB, our aim is to develop improved models capable of recognizing all important behaviors accurately and to assist other researchers and practitioners in developing and evaluating new ML models for cattle behavior classification using video data.

Authors:Zheng Li, Caili Guo, Xin Wang, Zerun Feng, Yanjun Wang

Abstract: Image-Text Retrieval (ITR) is essentially a ranking problem. Given a query caption, the goal is to rank candidate images by relevance, from large to small. The current ITR datasets are constructed in a pairwise manner. Image-text pairs are annotated as positive or negative. Correspondingly, ITR models mainly use pairwise losses, such as triplet loss, to learn to rank. Pairwise-based ITR increases positive pair similarity while decreasing negative pair similarity indiscriminately. However, the relevance between dissimilar negative pairs is different. Pairwise annotations cannot reflect this difference in relevance. In the current datasets, pairwise annotations miss many correlations. There are many potential positive pairs among the pairs labeled as negative. Pairwise-based ITR can only rank positive samples before negative samples, but cannot rank negative samples by relevance. In this paper, we integrate listwise ranking into conventional pairwise-based ITR. Listwise ranking optimizes the entire ranking list based on relevance scores. Specifically, we first propose a Relevance Score Calculation (RSC) module to calculate the relevance score of the entire ranked list. Then we choose the ranking metric, Normalized Discounted Cumulative Gain (NDCG), as the optimization objective. We transform the non-differentiable NDCG into a differentiable listwise loss, named Smooth-NDCG (S-NDCG). Our listwise ranking approach can be plug-and-play integrated into current pairwise-based ITR models. Experiments on ITR benchmarks show that integrating listwise ranking can improve the performance of current ITR models and provide more user-friendly retrieval results. The code is available at https://github.com/AAA-Zheng/Listwise_ITR.

Authors:Xue Zhang, Xiaohan Zhang, Zehua Sheng, Hui-Liang Shen

Abstract: Pedestrian detection is a critical task in computer vision because of its role in ensuring traffic safety. However, existing methods that rely solely on RGB images suffer from performance degradation under low-light conditions due to the lack of useful information. To address this issue, recent multispectral detection approaches combine thermal images to provide complementary information. Nevertheless, these approaches have limitations such as the noisy fused feature maps and the loss of informative features. In this paper, we propose a novel target-aware fusion strategy for multispectral pedestrian detection, named TFDet. Unlike existing methods, TFDet enhances features by supervising the fusion process with a correlation-maximum loss function. Our fusion strategy highlights the pedestrian-related features while suppressing the unrelated ones. TFDet achieves state-of-the-art performances on both KAIST and LLVIP benchmarks, with a speed comparable to the previous state-of-the-art counterpart. Importantly, TFDet performs remarkably well under low-light conditions, which is a significant advancement for road safety.

Authors:Sathyanarayanan N. Aakur, Sanjoy Kundu, Shubham Trehan

Abstract: Learning to infer labels in an open world, i.e., in an environment where the target ``labels'' are unknown, is an important characteristic for achieving autonomy. Foundation models pre-trained on enormous amounts of data have shown remarkable generalization skills through prompting, particularly in zero-shot inference. However, their performance is restricted to the correctness of the target label's search space. In an open world where these labels are unknown, the search space can be exceptionally large. It can require reasoning over several combinations of elementary concepts to arrive at an inference, which severely restricts the performance of such models. To tackle this challenging problem, we propose a neuro-symbolic framework called ALGO - novel Action Learning with Grounded Object recognition that can use symbolic knowledge stored in large-scale knowledge bases to infer activities (verb-noun combinations) in egocentric videos with limited supervision using two steps. First, we propose a novel neuro-symbolic prompting approach that uses object-centric vision-language foundation models as a noisy oracle to ground objects in the video through evidence-based reasoning. Second, driven by prior commonsense knowledge, we discover plausible activities through an energy-based symbolic pattern theory framework and learn to ground knowledge-based action (verb) concepts in the video. Extensive experiments on two publicly available datasets (GTEA Gaze and GTEA Gaze Plus) demonstrate its performance on open-world activity inference and its generalization to unseen actions in an unknown search space. We show that ALGO can be extended to zero-shot settings and demonstrate its competitive performance to multimodal foundation models.

Authors:Zhiwen Fan, Panwang Pan, Peihao Wang, Yifan Jiang, Dejia Xu, Hanwen Jiang, Zhangyang Wang

Abstract: Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation, existing methods have limited applicability in real-world scenarios involving embodied agents and downstream 3D vision tasks. These limitations mainly come from the necessity of 3D models, closed-category detection, and a large number of densely annotated support views. To mitigate this issue, we propose a general paradigm for object pose estimation, called Promptable Object Pose Estimation (POPE). The proposed approach POPE enables zero-shot 6DoF object pose estimation for any target object in any scene, while only a single reference is adopted as the support view. To achieve this, POPE leverages the power of the pre-trained large-scale 2D foundation model, employs a framework with hierarchical feature representation and 3D geometry principles. Moreover, it estimates the relative camera pose between object prompts and the target object in new views, enabling both two-view and multi-view 6DoF pose estimation tasks. Comprehensive experimental results demonstrate that POPE exhibits unrivaled robust performance in zero-shot settings, by achieving a significant reduction in the averaged Median Pose Error by 52.38% and 50.47% on the LINEMOD and OnePose datasets, respectively. We also conduct more challenging testings in causally captured images (see Figure 1), which further demonstrates the robustness of POPE. Project page can be found with https://paulpanwang.github.io/POPE/.

Authors:Ming Gao, YanWu Xu, Yang Zhao, Tingbo Hou, Chenkai Zhao, Mingming Gong

Abstract: In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler). We aim at stylizing any 3D scene with an arbitrary style from a text description, and synthesizing the novel stylized view, which is more flexible than the image-conditioned style transfer. Compared with the previous 2D method CLIPStyler, we are able to stylize a 3D scene and generalize to novel scenes without re-train our model. A straightforward solution is to combine previous image-conditioned 3D style transfer and text-conditioned 2D style transfer \bigskip methods. However, such a solution cannot achieve our goal due to two main challenges. First, there is no multi-modal model matching point clouds and language at different feature scales (low-level, high-level). Second, we observe a style mixing issue when we stylize the content with different style conditions from text prompts. To address the first issue, we propose a 3D stylization framework to match the point cloud features with text features in local and global views. For the second issue, we propose an improved directional divergence loss to make arbitrary text styles more distinguishable as a complement to our framework. We conduct extensive experiments to show the effectiveness of our model on text-guided 3D scene style transfer.

Authors:Gwantae Kim, Seonghyeok Noh, Insung Ham, Hanseok Ko

Abstract: When virtual agents interact with humans, gestures are crucial to delivering their intentions with speech. Previous multimodal co-speech gesture generation models required encoded features of all modalities to generate gestures. If some input modalities are removed or contain noise, the model may not generate the gestures properly. To acquire robust and generalized encodings, we propose a novel framework with a multimodal pre-trained encoder for co-speech gesture generation. In the proposed method, the multi-head-attention-based encoder is trained with self-supervised learning to contain the information on each modality. Moreover, we collect full-body gestures that consist of 3D joint rotations to improve visualization and apply gestures to the extensible body model. Through the series of experiments and human evaluation, the proposed method renders realistic co-speech gestures not only when all input modalities are given but also when the input modalities are missing or noisy.

Authors:Cheng Luo, Siyang Song, Weicheng Xie, Micol Spitale, Linlin Shen, Hatice Gunes

Abstract: In dyadic interaction, predicting the listener's facial reactions is challenging as different reactions may be appropriate in response to the same speaker's behaviour. This paper presents a novel framework called ReactFace that learns an appropriate facial reaction distribution from a speaker's behaviour rather than replicating the real facial reaction of the listener. ReactFace generates multiple different but appropriate photo-realistic human facial reactions by (i) learning an appropriate facial reaction distribution representing multiple appropriate facial reactions; and (ii) synchronizing the generated facial reactions with the speaker's verbal and non-verbal behaviours at each time stamp, resulting in realistic 2D facial reaction sequences. Experimental results demonstrate the effectiveness of our approach in generating multiple diverse, synchronized, and appropriate facial reactions from each speaker's behaviour, with the quality of the generated reactions being influenced by the speaker's speech and facial behaviours. Our code is made publicly available at \url{https://github.com/lingjivoo/ReactFace}.

Authors:Weizhi Nie, Ruidong Chen, Weijie Wang, Bruno Lepri, Nicu Sebe

Abstract: In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models efficiently from textual descriptions is a promising but challenging way to solve this problem. In this paper, inspired by the ability of human beings to complement visual information details from ambiguous descriptions based on their own experience, we propose a novel text-3D generation model (T2TD), which introduces the related shapes or textual information as the prior knowledge to improve the performance of the 3D generation model. In this process, we first introduce the text-3D knowledge graph to save the relationship between 3D models and textual semantic information, which can provide the related shapes to guide the target 3D model generation. Second, we integrate an effective causal inference model to select useful feature information from these related shapes, which removes the unrelated shape information and only maintains feature information that is strongly relevant to the textual description. Meanwhile, to effectively integrate multi-modal prior knowledge into textual information, we adopt a novel multi-layer transformer structure to progressively fuse related shape and textual information, which can effectively compensate for the lack of structural information in the text and enhance the final performance of the 3D generation model. The final experimental results demonstrate that our approach significantly improves 3D model generation quality and outperforms the SOTA methods on the text2shape datasets.

Authors:Aihua Zheng, Ziling He, Zi Wang, Chenglong Li, Jin Tang

Abstract: Many existing multi-modality studies are based on the assumption of modality integrity. However, the problem of missing arbitrary modalities is very common in real life, and this problem is less studied, but actually important in the task of multi-modality person re-identification (Re-ID). To this end, we design a novel dynamic enhancement network (DENet), which allows missing arbitrary modalities while maintaining the representation ability of multiple modalities, for partial multi-modality person Re-ID. To be specific, the multi-modal representation of the RGB, near-infrared (NIR) and thermal-infrared (TIR) images is learned by three branches, in which the information of missing modalities is recovered by the feature transformation module. Since the missing state might be changeable, we design a dynamic enhancement module, which dynamically enhances modality features according to the missing state in an adaptive manner, to improve the multi-modality representation. Extensive experiments on multi-modality person Re-ID dataset RGBNT201 and vehicle Re-ID dataset RGBNT100 comparing to the state-of-the-art methods verify the effectiveness of our method in complex and changeable environments.

Authors:Aihua Zheng, Chaobin Zhang, Weijun Zhang, Chenglong Li, Jin Tang, Chang Tan, Ruoran Jia

Abstract: Existing vehicle re-identification methods mainly rely on the single query, which has limited information for vehicle representation and thus significantly hinders the performance of vehicle Re-ID in complicated surveillance networks. In this paper, we propose a more realistic and easily accessible task, called multi-query vehicle Re-ID, which leverages multiple queries to overcome viewpoint limitation of single one. Based on this task, we make three major contributions. First, we design a novel viewpoint-conditioned network (VCNet), which adaptively combines the complementary information from different vehicle viewpoints, for multi-query vehicle Re-ID. Moreover, to deal with the problem of missing vehicle viewpoints, we propose a cross-view feature recovery module which recovers the features of the missing viewpoints by learnt the correlation between the features of available and missing viewpoints. Second, we create a unified benchmark dataset, taken by 6142 cameras from a real-life transportation surveillance system, with comprehensive viewpoints and large number of crossed scenes of each vehicle for multi-query vehicle Re-ID evaluation. Finally, we design a new evaluation metric, called mean cross-scene precision (mCSP), which measures the ability of cross-scene recognition by suppressing the positive samples with similar viewpoints from same camera. Comprehensive experiments validate the superiority of the proposed method against other methods, as well as the effectiveness of the designed metric in the evaluation of multi-query vehicle Re-ID.

Authors:Wenhao Cheng, Junbo Yin, Wei Li, Ruigang Yang, Jianbing Shen

Abstract: This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus on the 2D or 3D-indoor domain, which is not suitable for accurately predicting the location of the queried 3D region in an autonomous driving scene. In addition, the upper-bound limitation and the heavy computation cost motivate us to explore a better solution. In this work, we propose a new multi-modal visual grounding task, termed LiDAR Grounding. Then we devise a Multi-modal Single Shot Grounding (MSSG) approach with an effective token fusion strategy. It jointly learns the LiDAR-based object detector with the language features and predicts the targeted region directly from the detector without any post-processing. Moreover, the image feature can be flexibly integrated into our approach to provide rich texture and color information. The cross-modal learning enforces the detector to concentrate on important regions in the point cloud by considering the informative language expressions, thus leading to much better accuracy and efficiency. Extensive experiments on the Talk2Car dataset demonstrate the effectiveness of the proposed methods. Our work offers a deeper insight into the LiDAR-based grounding task and we expect it presents a promising direction for the autonomous driving community.

Authors:Jian-Nan Su, Min Gan, Guang-Yong Chen, Wenzhong Guo, C. L. Philip Chen

Abstract: Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR). Researchers usually used the NLA to explore non-local self-similarity (NSS) in SISR and achieve satisfactory reconstruction results. However, a surprising phenomenon that the reconstruction performance of the standard NLA is similar to the NLA with randomly selected regions stimulated our interest to revisit NLA. In this paper, we first analyzed the attention map of the standard NLA from different perspectives and discovered that the resulting probability distribution always has full support for every local feature, which implies a statistical waste of assigning values to irrelevant non-local features, especially for SISR which needs to model long-range dependence with a large number of redundant non-local features. Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution. Furthermore, we derived some key properties of the soft thresholding operation that enable training our HSPA in an end-to-end manner. The HSPA can be integrated into existing deep SISR models as an efficient general building block. In addition, to demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN) by integrating a few HSPAs in a simple backbone. Extensive experimental results demonstrate that HSPAN outperforms state-of-the-art approaches on both quantitative and qualitative evaluations.

Authors:Saisai Ding, Juncheng Li, Jun Wang, Shihui Ying, Jun Shi

Abstract: The multi-scale information among the whole slide images (WSIs) is essential for cancer diagnosis. Although the existing multi-scale vision Transformer has shown its effectiveness for learning multi-scale image representation, it still cannot work well on the gigapixel WSIs due to their extremely large image sizes. To this end, we propose a novel Multi-scale Efficient Graph-Transformer (MEGT) framework for WSI classification. The key idea of MEGT is to adopt two independent Efficient Graph-based Transformer (EGT) branches to process the low-resolution and high-resolution patch embeddings (i.e., tokens in a Transformer) of WSIs, respectively, and then fuse these tokens via a multi-scale feature fusion module (MFFM). Specifically, we design an EGT to efficiently learn the local-global information of patch tokens, which integrates the graph representation into Transformer to capture spatial-related information of WSIs. Meanwhile, we propose a novel MFFM to alleviate the semantic gap among different resolution patches during feature fusion, which creates a non-patch token for each branch as an agent to exchange information with another branch by cross-attention. In addition, to expedite network training, a novel token pruning module is developed in EGT to reduce the redundant tokens. Extensive experiments on TCGA-RCC and CAMELYON16 datasets demonstrate the effectiveness of the proposed MEGT.

Authors:Jooyoung Choi, Yunjey Choi, Yunji Kim, Junho Kim, Sungroh Yoon

Abstract: Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to support text-guided image editing. While text guidance is an intuitive editing interface for users, it often fails to ensure the precise concept conveyed by users. To address this issue, we propose Custom-Edit, in which we (i) customize a diffusion model with a few reference images and then (ii) perform text-guided editing. Our key discovery is that customizing only language-relevant parameters with augmented prompts improves reference similarity significantly while maintaining source similarity. Moreover, we provide our recipe for each customization and editing process. We compare popular customization methods and validate our findings on two editing methods using various datasets.

Authors:Zhiwei Hao, Jianyuan Guo, Kai Han, Han Hu, Chang Xu, Yunhe Wang

Abstract: The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we identify the \emph{small data pitfall} that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K. Specifically, we show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1\%, 84.3\%, and 85.0\% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at https://github.com/Hao840/vanillaKD.

Authors:Yiqi Lin, Hao Wu, Ruichen Wang, Haonan Lu, Xiaodong Lin, Hui Xiong, Lin Wang

Abstract: Generating and editing a 3D scene guided by natural language poses a challenge, primarily due to the complexity of specifying the positional relations and volumetric changes within the 3D space. Recent advancements in Large Language Models (LLMs) have demonstrated impressive reasoning, conversational, and zero-shot generation abilities across various domains. Surprisingly, these models also show great potential in realizing and interpreting the 3D space. In light of this, we propose a novel language-guided interactive 3D generation system, dubbed LI3D, that integrates LLMs as a 3D layout interpreter into the off-the-shelf layout-to-3D generative models, allowing users to flexibly and interactively generate visual content. Specifically, we design a versatile layout structure base on the bounding boxes and semantics to prompt the LLMs to model the spatial generation and reasoning from language. Our system also incorporates LLaVA, a large language and vision assistant, to provide generative feedback from the visual aspect for improving the visual quality of generated content. We validate the effectiveness of LI3D, primarily in 3D generation and editing through multi-round interactions, which can be flexibly extended to 2D generation and editing. Various experiments demonstrate the potential benefits of incorporating LLMs in generative AI for applications, e.g., metaverse. Moreover, we benchmark the layout reasoning performance of LLMs with neural visual artist tasks, revealing their emergent ability in the spatial layout domain.

Authors:Liyao Tang, Zhe Chen, Shanshan Zhao, Chaoyue Wang, Dacheng Tao

Abstract: Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. Existing methods often rely on empirical label selection strategies, such as confidence thresholding, to generate beneficial pseudo-labels for model training. This approach may, however, hinder the comprehensive exploitation of unlabeled data points. We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly. To address this issue, we propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions. More specifically, our method introduces an Entropy Regularization loss and a Distribution Alignment loss for weakly supervised learning in 3D segmentation tasks, resulting in an ERDA learning strategy. Interestingly, by using KL distance to formulate the distribution alignment loss, it reduces to a deceptively simple cross-entropy-based loss which optimizes both the pseudo-label generation network and the 3D segmentation network simultaneously. Despite the simplicity, our method promisingly improves the performance. We validate the effectiveness through extensive experiments on various baselines and large-scale datasets. Results show that ERDA effectively enables the effective usage of all unlabeled data points for learning and achieves state-of-the-art performance under different settings. Remarkably, our method can outperform fully-supervised baselines using only 1% of true annotations. Code and model will be made publicly available.

Authors:Daniel Köhler, Maurice Quach, Michael Ulrich, Frank Meinl, Bastian Bischoff, Holger Blume

Abstract: Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense grid structure is often associated with a loss of information, due to the discretization and aggregation of points. In this paper, we propose a novel architecture, multi-scale KPPillarsBEV, that aims to mitigate the negative effects of grid rendering. Specifically, we propose a novel grid rendering method, KPBEV, which leverages the descriptive power of kernel point convolutions to improve the encoding of local point cloud contexts during grid rendering. In addition, we propose a general multi-scale grid rendering formulation to incorporate multi-scale feature maps into convolutional backbones of detection networks with arbitrary grid rendering methods. We perform extensive experiments on the nuScenes dataset and evaluate the methods in terms of detection performance and computational complexity. The proposed multi-scale KPPillarsBEV architecture outperforms the baseline by 5.37% and the previous state of the art by 2.88% in Car AP4.0 (average precision for a matching threshold of 4 meters) on the nuScenes validation set. Moreover, the proposed single-scale KPBEV grid rendering improves the Car AP4.0 by 2.90% over the baseline while maintaining the same inference speed.

Authors:Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi, Tomáš Rebok

Abstract: Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large volumes of such spatio-temporal skeleton data still remains a challenging problem. In this paper, we propose a novel content-based text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural-language textual description. To define baselines for this uncharted task, we employ the BERT and CLIP language representations to encode the text modality and successful spatio-temporal models to encode the motion modality. We additionally introduce our transformer-based approach, called Motion Transformer (MoT), which employs divided space-time attention to effectively aggregate the different skeleton joints in space and time. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions. Finally, we set up a common evaluation protocol by defining qualitative metrics for assessing the quality of the retrieved motions, targeting the two recently-introduced KIT Motion-Language and HumanML3D datasets. The code for reproducing our results is available at https://github.com/mesnico/text-to-motion-retrieval.

Authors:Risheng Liu, Zhu Liu, Jinyuan Liu, Xin Fan, Zhongxuan Luo

Abstract: Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an individual task, thus ignoring its underlying relationship with these downstream vision problems. Furthermore, designing proper fusion architectures often requires huge engineering labor. It also lacks mechanisms to improve the flexibility and generalization ability of current fusion approaches. To mitigate these issues, we establish a Task-guided, Implicit-searched and Meta-initialized (TIM) deep model to address the image fusion problem in a challenging real-world scenario. Specifically, we first propose a constrained strategy to incorporate information from downstream tasks to guide the unsupervised learning process of image fusion. Within this framework, we then design an implicit search scheme to automatically discover compact architectures for our fusion model with high efficiency. In addition, a pretext meta initialization technique is introduced to leverage divergence fusion data to support fast adaptation for different kinds of image fusion tasks. Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e.g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM. The source code will be available at https://github.com/LiuZhu-CV/TIMFusion.

Authors:Tsu-Ching Hsiao, Hao-Wei Chen, Hsuan-Kung Yang, Chun-Yi Lee

Abstract: Addressing accuracy limitations and pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions. In response, we introduce a novel score-based diffusion method applied to the $SE(3)$ group, marking the first application of diffusion models to $SE(3)$ within the image domain, specifically tailored for pose estimation tasks. Extensive evaluations demonstrate the method's efficacy in handling pose ambiguity, mitigating perspective-induced ambiguity, and showcasing the robustness of our surrogate Stein score formulation on $SE(3)$. This formulation not only improves the convergence of Langevin dynamics but also enhances computational efficiency. Thus, we pioneer a promising strategy for 6D object pose estimation.

Authors:Lukas Stäcker, Shashank Mishra, Philipp Heidenreich, Jason Rambach, Didier Stricker

Abstract: Radars and cameras belong to the most frequently used sensors for advanced driver assistance systems and automated driving research. However, there has been surprisingly little research on radar-camera fusion with neural networks. One of the reasons is a lack of large-scale automotive datasets with radar and unmasked camera data, with the exception of the nuScenes dataset. Another reason is the difficulty of effectively fusing the sparse radar point cloud on the bird's eye view (BEV) plane with the dense images on the perspective plane. The recent trend of camera-based 3D object detection using BEV features has enabled a new type of fusion, which is better suited for radars. In this work, we present RC-BEVFusion, a modular radar-camera fusion network on the BEV plane. We propose BEVFeatureNet, a novel radar encoder branch, and show that it can be incorporated into several state-of-the-art camera-based architectures. We show significant performance gains of up to 28% increase in the nuScenes detection score, which is an important step in radar-camera fusion research. Without tuning our model for the nuScenes benchmark, we achieve the best result among all published methods in the radar-camera fusion category.

Authors:Yutao Cui, Tianhui Song, Gangshan Wu, Limin Wang

Abstract: Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a fully transformer tracking framework, coined as \emph{MixFormerV2}, without any dense convolutional operation and complex score prediction module. Our key design is to introduce four special prediction tokens and concatenate them with the tokens from target template and search areas. Then, we apply the unified transformer backbone on these mixed token sequence. These prediction tokens are able to capture the complex correlation between target template and search area via mixed attentions. Based on them, we can easily predict the tracking box and estimate its confidence score through simple MLP heads. To further improve the efficiency of MixFormerV2, we present a new distillation-based model reduction paradigm, including dense-to-sparse distillation and deep-to-shallow distillation. The former one aims to transfer knowledge from the dense-head based MixViT to our fully transformer tracker, while the latter one is used to prune some layers of the backbone. We instantiate two types of MixForemrV2, where the MixFormerV2-B achieves an AUC of 70.6\% on LaSOT and an AUC of 57.4\% on TNL2k with a high GPU speed of 165 FPS, and the MixFormerV2-S surpasses FEAR-L by 2.7\% AUC on LaSOT with a real-time CPU speed.

Authors:Hantao Yao, Lu Yu, Jifei Luo, Changsheng Xu

Abstract: Object Re-identification (ReID) aims to retrieve the probe object from many gallery images with the ReID model inferred based on a stationary camera-free dataset by associating and collecting the identities across all camera views. When deploying the ReID algorithm in real-world scenarios, the aspect of storage, privacy constraints, and dynamic changes of cameras would degrade its generalizability and applicability. Treating each camera's data independently, we introduce a novel ReID task named Camera-Incremental Object Re-identification (CIOR) by continually optimizing the ReID mode from the incoming stream of the camera dataset. Since the identities under different camera views might describe the same object, associating and distilling the knowledge of common identities would boost the discrimination and benefit from alleviating the catastrophic forgetting. In this paper, we propose a novel Identity Knowledge Evolution (IKE) framework for CIOR, consisting of the Identity Knowledge Association (IKA), Identity Knowledge Distillation (IKD), and Identity Knowledge Update (IKU). IKA is proposed to discover the common identities between the current identity and historical identities. IKD has applied to distillate historical identity knowledge from common identities and quickly adapt the historical model to the current camera view. After each camera has been trained, IKU is applied to continually expand the identity knowledge by combining the historical and current identity memories. The evaluation of Market-CL and Veri-CL shows the Identity Knowledge Evolution (IKE) effectiveness for CIOR. code:https://github.com/htyao89/Camera-Incremental-Object-ReID

Authors:Chenglin Yao, Jianfeng Ren, Ruibin Bai, Heshan Du, Jiang Liu, Xudong Jiang

Abstract: Detecting 3D mask attacks to a face recognition system is challenging. Although genuine faces and 3D face masks show significantly different remote photoplethysmography (rPPG) signals, rPPG-based face anti-spoofing methods often suffer from performance degradation due to unstable face alignment in the video sequence and weak rPPG signals. To enhance the rPPG signal in a motion-robust way, a landmark-anchored face stitching method is proposed to align the faces robustly and precisely at the pixel-wise level by using both SIFT keypoints and facial landmarks. To better encode the rPPG signal, a weighted spatial-temporal representation is proposed, which emphasizes the face regions with rich blood vessels. In addition, characteristics of rPPG signals in different color spaces are jointly utilized. To improve the generalization capability, a lightweight EfficientNet with a Gated Recurrent Unit (GRU) is designed to extract both spatial and temporal features from the rPPG spatial-temporal representation for classification. The proposed method is compared with the state-of-the-art methods on five benchmark datasets under both intra-dataset and cross-dataset evaluations. The proposed method shows a significant and consistent improvement in performance over other state-of-the-art rPPG-based methods for face spoofing detection.

Authors:Anthony Knittel, Morris Antonello, John Redford, Subramanian Ramamoorthy

Abstract: The ability to anticipate pedestrian motion changes is a critical capability for autonomous vehicles. In urban environments, pedestrians may enter the road area and create a high risk for driving, and it is important to identify these cases. Typical predictors use the trajectory history to predict future motion, however in cases of motion initiation, motion in the trajectory may only be clearly visible after a delay, which can result in the pedestrian has entered the road area before an accurate prediction can be made. Appearance data includes useful information such as changes of gait, which are early indicators of motion changes, and can inform trajectory prediction. This work presents a comparative evaluation of trajectory-only and appearance-based methods for pedestrian prediction, and introduces a new dataset experiment for prediction using appearance. We create two trajectory and image datasets based on the combination of image and trajectory sequences from the popular NuScenes dataset, and examine prediction of trajectories using observed appearance to influence futures. This shows some advantages over trajectory prediction alone, although problems with the dataset prevent advantages of appearance-based models from being shown. We describe methods for improving the dataset and experiment to allow benefits of appearance-based models to be captured.

Authors:Arian Mousakhan, Thomas Brox, Jawad Tayyub

Abstract: Reconstruction-based methods have struggled to achieve competitive performance on anomaly detection. In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD). We propose a novel denoising process for image reconstruction conditioned on a target image. This results in a coherent restoration that closely resembles the target image. Subsequently, our anomaly detection framework leverages this conditioning where the target image is set as the input image to guide the denoising process, leading to defectless reconstruction while maintaining nominal patterns. We localise anomalies via a pixel-wise and feature-wise comparison of the input and reconstructed image. Finally, to enhance the effectiveness of feature comparison, we introduce a domain adaptation method that utilises generated examples from our conditioned denoising process to fine-tune the feature extractor. The veracity of the approach is demonstrated on various datasets including MVTec and VisA benchmarks, achieving state-of-the-art results of 99.5% and 99.3% image-level AUROC respectively.

Authors:Sitian Shen, Zilin Zhu, Linqian Fan, Harry Zhang, Xinxiao Wu

Abstract: Large pre-trained models have had a significant impact on computer vision by enabling multi-modal learning, where the CLIP model has achieved impressive results in image classification, object detection, and semantic segmentation. However, the model's performance on 3D point cloud processing tasks is limited due to the domain gap between depth maps from 3D projection and training images of CLIP. This paper proposes DiffCLIP, a new pre-training framework that incorporates stable diffusion with ControlNet to minimize the domain gap in the visual branch. Additionally, a style-prompt generation module is introduced for few-shot tasks in the textual branch. Extensive experiments on the ModelNet10, ModelNet40, and ScanObjectNN datasets show that DiffCLIP has strong abilities for 3D understanding. By using stable diffusion and style-prompt generation, DiffCLIP achieves an accuracy of 43.2\% for zero-shot classification on OBJ\_BG of ScanObjectNN, which is state-of-the-art performance, and an accuracy of 80.6\% for zero-shot classification on ModelNet10, which is comparable to state-of-the-art performance.

Authors:Zihao Zhao, Sheng Wang, Jinchen Gu, Yitao Zhu, Lanzhuju Mei, Zixu Zhuang, Zhiming Cui, Qian Wang, Dinggang Shen

Abstract: The potential of integrating Computer-Assisted Diagnosis (CAD) with Large Language Models (LLMs) in clinical applications, particularly in digital family doctor and clinic assistant roles, shows promise. However, existing works have limitations in terms of reliability, effectiveness, and their narrow applicability to specific image domains, which restricts their overall processing capabilities. Moreover, the mismatch in writing style between LLMs and radiologists undermines their practical utility. To address these challenges, we present ChatCAD+, an interactive CAD system that is universal, reliable, and capable of handling medical images from diverse domains. ChatCAD+ utilizes current information obtained from reputable medical websites to offer precise medical advice. Additionally, it incorporates a template retrieval system that emulates real-world diagnostic reporting, thereby improving its seamless integration into existing clinical workflows. The source code is available at https://github.com/zhaozh10/ChatCAD. The online demo will be available soon.

Authors:Isabelle Tulleners, Tobias Moers, Thomas Schulik, Martin Sedlacek

Abstract: In order to deploy automated vehicles to the public, it has to be proven that the vehicle can safely and robustly handle traffic in many different scenarios. One important component of automated vehicles is the perception system that captures and processes the environment around the vehicle. Perception systems require large datasets for training their deep neural network. Knowing which parts of the data in these datasets describe a corner case is an advantage during training or testing of the network. These corner cases describe situations that are rare and potentially challenging for the network. We propose a pipeline that converts collective expert knowledge descriptions into the extended KI Absicherung ontology. The ontology is used to describe scenes and scenarios that can be mapped to perception datasets. The corner cases can then be extracted from the datasets. In addition, the pipeline enables the evaluation of the detection networks against the extracted corner cases to measure their performance.

Authors:Xijun Wang, Dongyang Liu, Meina Kan, Chunrui Han, Zhongqin Wu, Shiguang Shan

Abstract: In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mimicking difficulty, we introduce a triplet knowledge distillation mechanism named TriKD. Besides teacher and student, TriKD employs a third role called anchor model. Before distillation begins, the pre-trained anchor model delimits a subspace within the full solution space of the target problem. Solutions within the subspace are expected to be easy targets that the student could mimic well. Distillation then begins in an online manner, and the teacher is only allowed to express solutions within the aforementioned subspace. Surprisingly, benefiting from accurate but easy-to-mimic hints, the student can finally perform well. After the student is well trained, it can be used as the new anchor for new students, forming a curriculum learning strategy. Our experiments on image classification and face recognition with various models clearly demonstrate the effectiveness of our method. Furthermore, the proposed TriKD is also effective in dealing with the overfitting issue. Moreover, our theoretical analysis supports the rationality of our triplet distillation.

Authors:Runsen Feng, Zongyu Guo, Weiping Li, Zhibo Chen

Abstract: In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance. Recent state-of-the-art methods for neural image compression are mainly based on nonlinear transform coding (NTC) with uniform scalar quantization, overlooking the benefits of VQ due to its exponentially increased complexity. In this paper, we first investigate on some toy sources, demonstrating that even if modern neural networks considerably enhance the compression performance of SQ with nonlinear transform, there is still an insurmountable chasm between SQ and VQ. Therefore, revolving around VQ, we propose a novel framework for neural image compression named Nonlinear Vector Transform Coding (NVTC). NVTC solves the critical complexity issue of VQ through (1) a multi-stage quantization strategy and (2) nonlinear vector transforms. In addition, we apply entropy-constrained VQ in latent space to adaptively determine the quantization boundaries for joint rate-distortion optimization, which improves the performance both theoretically and experimentally. Compared to previous NTC approaches, NVTC demonstrates superior rate-distortion performance, faster decoding speed, and smaller model size. Our code is available at https://github.com/USTC-IMCL/NVTC

Authors:Thomas Eboli, Jean-Michel Morel, Gabriele Facciolo

Abstract: Blurry images usually exhibit similar blur at various locations across the image domain, a property barely captured in nowadays blind deblurring neural networks. We show that when extracting patches of similar underlying blur is possible, jointly processing the stack of patches yields superior accuracy than handling them separately. Our collaborative scheme is implemented in a neural architecture with a pooling layer on the stack dimension. We present three practical patch extraction strategies for image sharpening, camera shake removal and optical aberration correction, and validate the proposed approach on both synthetic and real-world benchmarks. For each blur instance, the proposed collaborative strategy yields significant quantitative and qualitative improvements.

Authors:Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, Alperen Tezcan, Ayse Gulnihan Simsek, Furkan Almas, Sevval Nil Esirgun, Hadrien Reynaud, Sarthak Pati, Christian Bluethgen, Bjoern Menze

Abstract: Generative modeling has experienced substantial progress in recent years, particularly in text-to-image and text-to-video synthesis. However, the medical field has not yet fully exploited the potential of large-scale foundational models for synthetic data generation. In this paper, we introduce GenerateCT, the first method for text-conditional computed tomography (CT) generation, addressing the limitations in 3D medical imaging research and making our entire framework open-source. GenerateCT consists of a pre-trained large language model, a transformer-based text-conditional 3D chest CT generation architecture, and a text-conditional spatial super-resolution diffusion model. We also propose CT-ViT, which efficiently compresses CT volumes while preserving auto-regressiveness in-depth, enabling the generation of 3D CT volumes with variable numbers of axial slices. Our experiments demonstrate that GenerateCT can produce realistic, high-resolution, and high-fidelity 3D chest CT volumes consistent with medical language text prompts. We further investigate the potential of GenerateCT by training a model using generated CT volumes for multi-abnormality classification of chest CT volumes. Our contributions provide a valuable foundation for future research in text-conditional 3D medical image generation and have the potential to accelerate advancements in medical imaging research. Our code, pre-trained models, and generated data are available at https://github.com/ibrahimethemhamamci/GenerateCT.

Authors:Lantian Li, Xiaolou Li, Haoyu Jiang, Chen Chen, Ruihai Hou, Dong Wang

Abstract: Audio-visual person recognition (AVPR) has received extensive attention. However, most datasets used for AVPR research so far are collected in constrained environments, and thus cannot reflect the true performance of AVPR systems in real-world scenarios. To meet the request for research on AVPR in unconstrained conditions, this paper presents a multi-genre AVPR dataset collected `in the wild', named CN-Celeb-AV. This dataset contains more than 420k video segments from 1,136 persons from public media. In particular, we put more emphasis on two real-world complexities: (1) data in multiple genres; (2) segments with partial information. A comprehensive study was conducted to compare CN-Celeb-AV with two popular public AVPR benchmark datasets, and the results demonstrated that CN-Celeb-AV is more in line with real-world scenarios and can be regarded as a new benchmark dataset for AVPR research. The dataset also involves a development set that can be used to boost the performance of AVPR systems in real-life situations. The dataset is free for researchers and can be downloaded from http://cnceleb.org/.

Authors:Sanket Thakur, Cigdem Beyan, Pietro Morerio, Vittorio Murino, Alessio Del Bue

Abstract: In this technical report, we describe the Guided-Attention mechanism based solution for the short-term anticipation (STA) challenge for the EGO4D challenge. It combines the object detections, and the spatiotemporal features extracted from video clips, enhancing the motion and contextual information, and further decoding the object-centric and motion-centric information to address the problem of STA in egocentric videos. For the challenge, we build our model on top of StillFast with Guided Attention applied on fast network. Our model obtains better performance on the validation set and also achieves state-of-the-art (SOTA) results on the challenge test set for EGO4D Short-Term Object Interaction Anticipation Challenge.

Authors:Zijia Zhao, Longteng Guo, Tongtian Yue, Sihan Chen, Shuai Shao, Xinxin Zhu, Zehuan Yuan, Jing Liu

Abstract: Building general-purpose models that can perceive diverse real-world modalities and solve various tasks is an appealing target in artificial intelligence. In this paper, we present ChatBridge, a novel multimodal language model that leverages the expressive capabilities of language as the catalyst to bridge the gap between various modalities. We show that only language-paired two-modality data is sufficient to connect all modalities. ChatBridge leverages recent large language models (LLM) and extends their zero-shot capabilities to incorporate diverse multimodal inputs. ChatBridge undergoes a two-stage training. The first stage aligns each modality with language, which brings emergent multimodal correlation and collaboration abilities. The second stage instruction-finetunes ChatBridge to align it with user intent with our newly proposed multimodal instruction tuning dataset, named MULTIS, which covers a wide range of 16 multimodal tasks of text, image, video, and audio modalities. We show strong quantitative and qualitative results on zero-shot multimodal tasks covering text, image, video, and audio modalities. All codes, data, and models of ChatBridge will be open-sourced.

Authors:Jiahao Yang, Wufei Ma, Angtian Wang, Xiaoding Yuan, Alan Yuille, Adam Kortylewski

Abstract: Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is time-consuming and challenging. While synthetically generated training data is a viable alternative, the domain shift between real and synthetic data is a significant challenge. In this work, we aim to narrow the performance gap between models trained on synthetic data and few real images and fully supervised models trained on large-scale data. We achieve this by approaching the problem from two perspectives: 1) We introduce SyntheticP3D, a new synthetic dataset for object pose estimation generated from CAD models and enhanced with a novel algorithm. 2) We propose a novel approach (CC3D) for training neural mesh models that perform pose estimation via inverse rendering. In particular, we exploit the spatial relationships between features on the mesh surface and a contrastive learning scheme to guide the domain adaptation process. Combined, these two approaches enable our models to perform competitively with state-of-the-art models using only 10% of the respective real training images, while outperforming the SOTA model by 10.4% with a threshold of pi/18 using only 50% of the real training data. Our trained model further demonstrates robust generalization to out-of-distribution scenarios despite being trained with minimal real data.

Authors:Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp, Marc Walessa, Daniel Meissner, Klaus Dietmayer

Abstract: Autonomous vehicles rely on LiDAR sensors to perceive the environment. Adverse weather conditions like rain, snow, and fog negatively affect these sensors, reducing their reliability by introducing unwanted noise in the measurements. In this work, we tackle this problem by proposing a novel approach for detecting adverse weather effects in LiDAR data. We reformulate this problem as an outlier detection task and use an energy-based framework to detect outliers in point clouds. More specifically, our method learns to associate low energy scores with inlier points and high energy scores with outliers allowing for robust detection of adverse weather effects. In extensive experiments, we show that our method performs better in adverse weather detection and has higher robustness to unseen weather effects than previous state-of-the-art methods. Furthermore, we show how our method can be used to perform simultaneous outlier detection and semantic segmentation. Finally, to help expand the research field of LiDAR perception in adverse weather, we release the SemanticSpray dataset, which contains labeled vehicle spray data in highway-like scenarios. The dataset is available at http://dx.doi.org/10.18725/OPARU-48815 .

Authors:Zhiyu Tan, Zichao Dong, Cheng Zhang, Weikun Zhang, Hang Ji, Hao Li

Abstract: Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment. Existing occupancy prediction methods are almost entirely trained on human-annotated volumetric data. Although of high quality, the generation of such 3D annotations is laborious and costly, restricting them to a few specific object categories in the training dataset. To address this limitation, this paper proposes Open Vocabulary Occupancy (OVO), a novel approach that allows semantic occupancy prediction of arbitrary classes but without the need for 3D annotations during training. Keys to our approach are (1) knowledge distillation from a pre-trained 2D open-vocabulary segmentation model to the 3D occupancy network, and (2) pixel-voxel filtering for high-quality training data generation. The resulting framework is simple, compact, and compatible with most state-of-the-art semantic occupancy prediction models. On NYUv2 and SemanticKITTI datasets, OVO achieves competitive performance compared to supervised semantic occupancy prediction approaches. Furthermore, we conduct extensive analyses and ablation studies to offer insights into the design of the proposed framework.

Authors:Ethan Wilson, Frederick Shic, Eakta Jain

Abstract: Face swapping combines one face's identity with another face's non-appearance attributes (expression, head pose, lighting) to generate a synthetic face. This technology is rapidly improving, but falls flat when reconstructing some attributes, particularly gaze. Image-based loss metrics that consider the full face do not effectively capture the perceptually important, yet spatially small, eye regions. Improving gaze in face swaps can improve naturalness and realism, benefiting applications in entertainment, human computer interaction, and more. Improved gaze will also directly improve Deepfake detection efforts, serving as ideal training data for classifiers that rely on gaze for classification. We propose a novel loss function that leverages gaze prediction to inform the face swap model during training and compare against existing methods. We find all methods to significantly benefit gaze in resulting face swaps.

Authors:Jiawei Qin, Takuru Shimoyama, Xucong Zhang, Yusuke Sugano

Abstract: Along with the recent development of deep neural networks, appearance-based gaze estimation has succeeded considerably when training and testing within the same domain. Compared to the within-domain task, the variance of different domains makes the cross-domain performance drop severely, preventing gaze estimation deployment in real-world applications. Among all the factors, ranges of head pose and gaze are believed to play a significant role in the final performance of gaze estimation, while collecting large ranges of data is expensive. This work proposes an effective model training pipeline consisting of a training data synthesis and a gaze estimation model for unsupervised domain adaptation. The proposed data synthesis leverages the single-image 3D reconstruction to expand the range of the head poses from the source domain without requiring a 3D facial shape dataset. To bridge the inevitable gap between synthetic and real images, we further propose an unsupervised domain adaptation method suitable for synthetic full-face data. We propose a disentangling autoencoder network to separate gaze-related features and introduce background augmentation consistency loss to utilize the characteristics of the synthetic source domain. Through comprehensive experiments, we show that the model only using monocular-reconstructed synthetic training data can perform comparably to real data with a large label range. Our proposed domain adaptation approach further improves the performance on multiple target domains. The code and data will be available at \url{https://github.com/ut-vision/AdaptiveGaze}.

Authors:Xiaomeng Yang, Zhi Qiao, Jin Wei, Yu Zhou, Ye Yuan, Zhilong Ji, Dongbao Yang, Weiping Wang

Abstract: Scene Text Recognition (STR) is a challenging task due to variations in text style, shape, and background. Incorporating linguistic information is an effective way to enhance the robustness of STR models. Existing methods rely on permuted language modeling (PLM) or masked language modeling (MLM) to learn contextual information implicitly, either through an ensemble of permuted autoregressive (AR) LMs training or iterative non-autoregressive (NAR) decoding procedure. However, these methods exhibit limitations: PLM's AR decoding results in the lack of information about future characters, while MLM provides global information of the entire text but neglects dependencies among each predicted character. In this paper, we propose a Masked and Permuted Implicit Context Learning Network for STR, which unifies PLM and MLM within a single decoding architecture, inheriting the advantages of both approaches. We utilize the training procedure of PLM, and to integrate MLM, we incorporate word length information into the decoding process by introducing specific numbers of mask tokens. Experimental results demonstrate that our proposed model achieves state-of-the-art performance on standard benchmarks using both AR and NAR decoding procedures.

Authors:Zhenxi Zhang, Ran Ran, Chunna Tian, Heng Zhou, Xin Li, Fan Yang, Zhicheng Jiao

Abstract: Consistency learning plays a crucial role in semi-supervised medical image segmentation as it enables the effective utilization of limited annotated data while leveraging the abundance of unannotated data. The effectiveness and efficiency of consistency learning are challenged by prediction diversity and training stability, which are often overlooked by existing studies. Meanwhile, the limited quantity of labeled data for training often proves inadequate for formulating intra-class compactness and inter-class discrepancy of pseudo labels. To address these issues, we propose a self-aware and cross-sample prototypical learning method (SCP-Net) to enhance the diversity of prediction in consistency learning by utilizing a broader range of semantic information derived from multiple inputs. Furthermore, we introduce a self-aware consistency learning method that exploits unlabeled data to improve the compactness of pseudo labels within each class. Moreover, a dual loss re-weighting method is integrated into the cross-sample prototypical consistency learning method to improve the reliability and stability of our model. Extensive experiments on ACDC dataset and PROMISE12 dataset validate that SCP-Net outperforms other state-of-the-art semi-supervised segmentation methods and achieves significant performance gains compared to the limited supervised training. Our code will come soon.

Authors:Zhenxi Zhang, Ran Ran, Chunna Tian, Heng Zhou, Fan Yang, Xin Li, Zhicheng Jiao

Abstract: Semi-supervised medical image segmentation offers a promising solution for large-scale medical image analysis by significantly reducing the annotation burden while achieving comparable performance. Employing this method exhibits a high degree of potential for optimizing the segmentation process and increasing its feasibility in clinical settings during translational investigations. Recently, cross-supervised training based on different co-training sub-networks has become a standard paradigm for this task. Still, the critical issues of sub-network disagreement and label-noise suppression require further attention and progress in cross-supervised training. This paper proposes a cross-supervised learning framework based on dual classifiers (DC-Net), including an evidential classifier and a vanilla classifier. The two classifiers exhibit complementary characteristics, enabling them to handle disagreement effectively and generate more robust and accurate pseudo-labels for unlabeled data. We also incorporate the uncertainty estimation from the evidential classifier into cross-supervised training to alleviate the negative effect of the error supervision signal. The extensive experiments on LA and Pancreas-CT dataset illustrate that DC-Net outperforms other state-of-the-art methods for semi-supervised segmentation. The code will be released soon.

Authors:Yihao Huang, Yue Cao, Tianlin Li, Felix Juefei-Xu, Di Lin, Ivor W. Tsang, Yang Liu, Qing Guo

Abstract: Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt (e.g., points, bounding boxes, or masks) and an input image, SAM is able to generate valid segment masks for all objects indicated by the prompts, presenting high generalization across diverse scenarios and being a general method for zero-shot transfer to downstream vision tasks. Nevertheless, it remains unclear whether SAM may introduce errors in certain threatening scenarios. Clarifying this is of significant importance for applications that require robustness, such as autonomous vehicles. In this paper, we aim to study the testing-time robustness of SAM under adversarial scenarios and common corruptions. To this end, we first build a testing-time robustness evaluation benchmark for SAM by integrating existing public datasets. Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness. Third, we study the robustness of SAM under diverse corruption types by evaluating SAM on corrupted datasets with different prompts. With experiments conducted on SA-1B and KITTI datasets, we find that SAM exhibits remarkable robustness against various corruptions, except for blur-related corruption. Furthermore, SAM remains susceptible to adversarial attacks, particularly when subjected to PGD and BIM attacks. We think such a comprehensive study could highlight the importance of the robustness issues of SAM and trigger a series of new tasks for SAM as well as downstream vision tasks.

Authors:Xingqian Xu, Jiayi Guo, Zhangyang Wang, Gao Huang, Irfan Essa, Humphrey Shi

Abstract: Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. Moreover, as commonly argued: "an image is worth a thousand words" - the attempt to describe a desired image with texts often ends up being ambiguous and cannot comprehensively cover delicate visual details, hence necessitating more additional controls from the visual domain. In this paper, we take a bold step forward: taking "Text" out of a pre-trained T2I diffusion model, to reduce the burdensome prompt engineering efforts for users. Our proposed framework, Prompt-Free Diffusion, relies on only visual inputs to generate new images: it takes a reference image as "context", an optional image structural conditioning, and an initial noise, with absolutely no text prompt. The core architecture behind the scene is Semantic Context Encoder (SeeCoder), substituting the commonly used CLIP-based or LLM-based text encoder. The reusability of SeeCoder also makes it a convenient drop-in component: one can also pre-train a SeeCoder in one T2I model and reuse it for another. Through extensive experiments, Prompt-Free Diffusion is experimentally found to (i) outperform prior exemplar-based image synthesis approaches; (ii) perform on par with state-of-the-art T2I models using prompts following the best practice; and (iii) be naturally extensible to other downstream applications such as anime figure generation and virtual try-on, with promising quality. Our code and models are open-sourced at https://github.com/SHI-Labs/Prompt-Free-Diffusion.

Authors:Xiaokang Chen, Jiaxiang Tang, Diwen Wan, Jingbo Wang, Gang Zeng

Abstract: This paper investigates the potential of enhancing Neural Radiance Fields (NeRF) with semantics to expand their applications. Although NeRF has been proven useful in real-world applications like VR and digital creation, the lack of semantics hinders interaction with objects in complex scenes. We propose to imitate the backbone feature of off-the-shelf perception models to achieve zero-shot semantic segmentation with NeRF. Our framework reformulates the segmentation process by directly rendering semantic features and only applying the decoder from perception models. This eliminates the need for expensive backbones and benefits 3D consistency. Furthermore, we can project the learned semantics onto extracted mesh surfaces for real-time interaction. With the state-of-the-art Segment Anything Model (SAM), our framework accelerates segmentation by 16 times with comparable mask quality. The experimental results demonstrate the efficacy and computational advantages of our approach. Project page: \url{https://me.kiui.moe/san/}.

Authors:Shady Abu-Hussein, Raja Giryes

Abstract: In recent years, Denoising Diffusion Probabilistic Models (DDPM) have caught significant attention. By composing a Markovian process that starts in the data domain and then gradually adds noise until reaching pure white noise, they achieve superior performance in learning data distributions. Yet, these models require a large number of diffusion steps to produce aesthetically pleasing samples, which is inefficient. In addition, unlike common generative adversarial networks, the latent space of diffusion models is not interpretable. In this work, we propose to generalize the denoising diffusion process into an Upsampling Diffusion Probabilistic Model (UDPM), in which we reduce the latent variable dimension in addition to the traditional noise level addition. As a result, we are able to sample images of size $256\times 256$ with only 7 diffusion steps, which is less than two orders of magnitude compared to standard DDPMs. We formally develop the Markovian diffusion processes of the UDPM, and demonstrate its generation capabilities on the popular FFHQ, LSUN horses, ImageNet, and AFHQv2 datasets. Another favorable property of UDPM is that it is very easy to interpolate its latent space, which is not the case with standard diffusion models. Our code is available online \url{https://github.com/shadyabh/UDPM}

Authors:Chetan Joshi, Lawry Sorenson, Ammon Wolfert, Dr. Mark Clement, Dr. Joseph Price, Dr. Kasey Buckles

Abstract: Progress in Automated Handwriting Recognition has been hampered by the lack of large training datasets. Nearly all research uses a set of small datasets that often cause models to overfit. We present CENSUS-HWR, a new dataset consisting of full English handwritten words in 1,812,014 gray scale images. A total of 1,865,134 handwritten texts from a vocabulary of 10,711 words in the English language are present in this collection. This dataset is intended to serve handwriting models as a benchmark for deep learning algorithms. This huge English handwriting recognition dataset has been extracted from the US 1930 and 1940 censuses taken by approximately 70,000 enumerators each year. The dataset and the trained model with their weights are freely available to download at https://censustree.org/data.html.

Authors:Guangyao Zhai, Evin Pinar Örnek, Shun-Cheng Wu, Yan Di, Federico Tombari, Nassir Navab, Benjamin Busam

Abstract: Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to lacking a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset will be released upon acceptance.

Authors:Lisa Dunlap, Alyssa Umino, Han Zhang, Jiezhi Yang, Joseph E. Gonzalez, Trevor Darrell

Abstract: Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or location. As such, we explore how natural language descriptions of the domains seen in training data can be used with large vision models trained on diverse pretraining datasets to generate useful variations of the training data. We introduce ALIA (Automated Language-guided Image Augmentation), a method which utilizes large vision and language models to automatically generate natural language descriptions of a dataset's domains and augment the training data via language-guided image editing. To maintain data integrity, a model trained on the original dataset filters out minimal image edits and those which corrupt class-relevant information. The resulting dataset is visually consistent with the original training data and offers significantly enhanced diversity. On fine-grained and cluttered datasets for classification and detection, ALIA surpasses traditional data augmentation and text-to-image generated data by up to 15\%, often even outperforming equivalent additions of real data. Code is avilable at https://github.com/lisadunlap/ALIA.

Authors:Chia-Wen Kuo, Zsolt Kira

Abstract: A great deal of progress has been made in image captioning, driven by research into how to encode the image using pre-trained models. This includes visual encodings (e.g. image grid features or detected objects) and more recently textual encodings (e.g. image tags or text descriptions of image regions). As more advanced encodings are available and incorporated, it is natural to ask: how to efficiently and effectively leverage the heterogeneous set of encodings? In this paper, we propose to regard the encodings as augmented views of the input image. The image captioning model encodes each view independently with a shared encoder efficiently, and a contrastive loss is incorporated across the encoded views in a novel way to improve their representation quality and the model's data efficiency. Our proposed hierarchical decoder then adaptively weighs the encoded views according to their effectiveness for caption generation by first aggregating within each view at the token level, and then across views at the view level. We demonstrate significant performance improvements of +5.6% CIDEr on MS-COCO and +12.9% CIDEr on Flickr30k compared to state of the arts, and conduct rigorous analyses to demonstrate the importance of each part of our design.

Authors:Matthew Chang, Aditya Prakash, Saurabh Gupta

Abstract: The analysis and use of egocentric videos for robotic tasks is made challenging by occlusion due to the hand and the visual mismatch between the human hand and a robot end-effector. In this sense, the human hand presents a nuisance. However, often hands also provide a valuable signal, e.g. the hand pose may suggest what kind of object is being held. In this work, we propose to extract a factored representation of the scene that separates the agent (human hand) and the environment. This alleviates both occlusion and mismatch while preserving the signal, thereby easing the design of models for downstream robotics tasks. At the heart of this factorization is our proposed Video Inpainting via Diffusion Model (VIDM) that leverages both a prior on real-world images (through a large-scale pre-trained diffusion model) and the appearance of the object in earlier frames of the video (through attention). Our experiments demonstrate the effectiveness of VIDM at improving inpainting quality on egocentric videos and the power of our factored representation for numerous tasks: object detection, 3D reconstruction of manipulated objects, and learning of reward functions, policies, and affordances from videos.

Authors:Zheyuan Liu, Weixuan Sun, Damien Teney, Stephen Gould

Abstract: Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these to a reference image embedding modified by the query text at test time. Such a pipeline is very efficient at test time since fast vector distances can be used to evaluate candidates, but modifying the reference image embedding guided only by a short textual description can be difficult, especially independent of potential candidates. An alternative approach is to allow interactions between the query and every possible candidate, i.e., reference-text-candidate triplets, and pick the best from the entire set. Though this approach is more discriminative, for large-scale datasets the computational cost is prohibitive since pre-computation of candidate embeddings is no longer possible. We propose to combine the merits of both schemes using a two-stage model. Our first stage adopts the conventional vector distancing metric and performs a fast pruning among candidates. Meanwhile, our second stage employs a dual-encoder architecture, which effectively attends to the input triplet of reference-text-candidate and re-ranks the candidates. Both stages utilize a vision-and-language pre-trained network, which has proven beneficial for various downstream tasks. Our method consistently outperforms state-of-the-art approaches on standard benchmarks for the task.

Authors:Yu Zeng, Mo Zhou, Yuan Xue, Vishal M. Patel

Abstract: Recent advances in deep generative models have led to the development of methods capable of synthesizing high-quality, realistic images. These models pose threats to society due to their potential misuse. Prior research attempted to mitigate these threats by detecting generated images, but the varying traces left by different generative models make it challenging to create a universal detector capable of generalizing to new, unseen generative models. In this paper, we propose to inject a universal adversarial signature into an arbitrary pre-trained generative model, in order to make its generated contents more detectable and traceable. First, the imperceptible optimal signature for each image can be found by a signature injector through adversarial training. Subsequently, the signature can be incorporated into an arbitrary generator by fine-tuning it with the images processed by the signature injector. In this way, the detector corresponding to the signature can be reused for any fine-tuned generator for tracking the generator identity. The proposed method is validated on the FFHQ and ImageNet datasets with various state-of-the-art generative models, consistently showing a promising detection rate. Code will be made publicly available at \url{https://github.com/zengxianyu/genwm}.

Authors:Omri Avrahami, Kfir Aberman, Ohad Fried, Daniel Cohen-Or, Dani Lischinski

Abstract: Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images with variations in backgrounds and poses, and struggle when adapted to a different scenario. In this work, we introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method. Project page is available at: https://omriavrahami.com/break-a-scene/

Authors:Carlos Rodriguez-Pardo, Henar Dominguez-Elvira, David Pascual-Hernandez, Elena Garces

Abstract: We propose a learning-based method to recover normals, specularity, and roughness from a single diffuse image of a material, using microgeometry appearance as our primary cue. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room for generalization. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room for generalization. In contrast, in this work, we propose a novel capture approach that leverages a generative network with attention and a U-Net discriminator, which shows outstanding performance integrating global information at reduced computational complexity. We showcase the performance of our method with a real dataset of digitized textile materials and show that a commodity flatbed scanner can produce the type of diffuse illumination required as input to our method. Additionally, because the problem might be illposed -more than a single diffuse image might be needed to disambiguate the specular reflection- or because the training dataset is not representative enough of the real distribution, we propose a novel framework to quantify the model's confidence about its prediction at test time. Our method is the first one to deal with the problem of modeling uncertainty in material digitization, increasing the trustworthiness of the process and enabling more intelligent strategies for dataset creation, as we demonstrate with an active learning experiment.

Authors:Congyue Deng, Jiahui Lei, Bokui Shen, Kostas Daniilidis, Leonidas Guibas

Abstract: Equivariance has gained strong interest as a desirable network property that inherently ensures robust generalization. However, when dealing with complex systems such as articulated objects or multi-object scenes, effectively capturing inter-part transformations poses a challenge, as it becomes entangled with the overall structure and local transformations. The interdependence of part assignment and per-part group action necessitates a novel equivariance formulation that allows for their co-evolution. In this paper, we present Banana, a Banach fixed-point network for equivariant segmentation with inter-part equivariance by construction. Our key insight is to iteratively solve a fixed-point problem, where point-part assignment labels and per-part SE(3)-equivariance co-evolve simultaneously. We provide theoretical derivations of both per-step equivariance and global convergence, which induces an equivariant final convergent state. Our formulation naturally provides a strict definition of inter-part equivariance that generalizes to unseen inter-part configurations. Through experiments conducted on both articulated objects and multi-object scans, we demonstrate the efficacy of our approach in achieving strong generalization under inter-part transformations, even when confronted with substantial changes in pointcloud geometry and topology.

Authors:Jiahui Lei, Congyue Deng, Bokui Shen, Leonidas Guibas, Kostas Daniilidis

Abstract: We propose Neural 3D Articulation Prior (NAP), the first 3D deep generative model to synthesize 3D articulated object models. Despite the extensive research on generating 3D objects, compositions, or scenes, there remains a lack of focus on capturing the distribution of articulated objects, a common object category for human and robot interaction. To generate articulated objects, we first design a novel articulation tree/graph parameterization and then apply a diffusion-denoising probabilistic model over this representation where articulated objects can be generated via denoising from random complete graphs. In order to capture both the geometry and the motion structure whose distribution will affect each other, we design a graph-attention denoising network for learning the reverse diffusion process. We propose a novel distance that adapts widely used 3D generation metrics to our novel task to evaluate generation quality, and experiments demonstrate our high performance in articulated object generation. We also demonstrate several conditioned generation applications, including Part2Motion, PartNet-Imagination, Motion2Part, and GAPart2Object.

Authors:Renan A. Rojas-Gomez, Teck-Yian Lim, Minh N. Do, Raymond A. Yeh

Abstract: For computer vision tasks, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs remain sensitive to small shifts in the input image. To address this, we introduce novel designs for each of the modules in ViTs, such as tokenization, self-attention, patch merging, and positional encoding. With our proposed modules, we achieve truly shift-equivariant ViTs on four well-established models, namely, Swin, SwinV2, MViTv2, and CvT, both in theory and practice. Empirically, we tested these models on image classification and semantic segmentation, achieving competitive performance across three different datasets while maintaining 100% shift consistency.

Authors:Shilin Yan, Renrui Zhang, Ziyu Guo, Wenchao Chen, Wei Zhang, Hongyang Li, Yu Qiao, Zhongjiang He, Peng Gao

Abstract: Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +4.2% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.

Authors:Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Youzuo Lin

Abstract: This paper reveals that every image can be understood as a first-order norm+linear autoregressive process, referred to as FINOLA, where norm+linear denotes the use of normalization before the linear model. We demonstrate that images of size 256$\times$256 can be reconstructed from a compressed vector using autoregression up to a 16$\times$16 feature map, followed by upsampling and convolution. This discovery sheds light on the underlying partial differential equations (PDEs) governing the latent feature space. Additionally, we investigate the application of FINOLA for self-supervised learning through a simple masked prediction technique. By encoding a single unmasked quadrant block, we can autoregressively predict the surrounding masked region. Remarkably, this pre-trained representation proves effective for image classification and object detection tasks, even in lightweight networks, without requiring fine-tuning. The code will be made publicly available.

Authors:Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Todd Zickler, Pratul P. Srinivasan

Abstract: Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This problem is ill-conditioned because diffuse materials severely blur incoming light, and is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination -- even from diffuse objects -- by exploiting unintended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatially-varying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who inadvertently cast shadows upon it.

Authors:Shihao Zhao, Dongdong Chen, Yen-Chun Chen, Jianmin Bao, Shaozhe Hao, Lu Yuan, Kwan-Yee K. Wong

Abstract: Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often struggle to adequately convey detailed controls, even when composed of long and complex texts. Moreover, recent studies have also shown that these models face challenges in understanding such complex texts and generating the corresponding images. Therefore, there is a growing need to enable more control modes beyond text description. In this paper, we introduce Uni-ControlNet, a novel approach that allows for the simultaneous utilization of different local controls (e.g., edge maps, depth map, segmentation masks) and global controls (e.g., CLIP image embeddings) in a flexible and composable manner within one model. Unlike existing methods, Uni-ControlNet only requires the fine-tuning of two additional adapters upon frozen pre-trained text-to-image diffusion models, eliminating the huge cost of training from scratch. Moreover, thanks to some dedicated adapter designs, Uni-ControlNet only necessitates a constant number (i.e., 2) of adapters, regardless of the number of local or global controls used. This not only reduces the fine-tuning costs and model size, making it more suitable for real-world deployment, but also facilitate composability of different conditions. Through both quantitative and qualitative comparisons, Uni-ControlNet demonstrates its superiority over existing methods in terms of controllability, generation quality and composability. Code is available at \url{https://github.com/ShihaoZhaoZSH/Uni-ControlNet}.

Authors:Benno Krojer, Elinor Poole-Dayan, Vikram Voleti, Christopher Pal, Siva Reddy

Abstract: Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis. We find that Stable Diffusion + DiffusionITM is competitive on many tasks and outperforms CLIP on compositional tasks like like CLEVR and Winoground. We further boost its compositional performance with a transfer setup by fine-tuning on MS-COCO while retaining generative capabilities. We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2.1 is, for the most part, less biased than Stable Diffusion 1.5. Overall, our results point in an exciting direction bringing discriminative and generative model evaluation closer. We will release code and benchmark setup soon.

Authors:Zihui Zhang, Bo Yang, Bing Wang, Bo Li

Abstract: We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes for every point in 3D scenes, without needing any type of human labels or pretrained models. The key to our approach is to discover 3D semantic elements via progressive growing of superpoints. Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation. We extensively evaluate our method on multiple datasets, demonstrating superior performance over all unsupervised baselines and approaching the classic fully-supervised PointNet. We hope our work could inspire more advanced methods for unsupervised 3D semantic learning.

Authors:Zhenzhen Weng, Zeyu Wang, Serena Yeung

Abstract: Recent advancements in text-to-image generation have enabled significant progress in zero-shot 3D shape generation. This is achieved by score distillation, a methodology that uses pre-trained text-to-image diffusion models to optimize the parameters of a 3D neural presentation, e.g. Neural Radiance Field (NeRF). While showing promising results, existing methods are often not able to preserve the geometry of complex shapes, such as human bodies. To address this challenge, we present ZeroAvatar, a method that introduces the explicit 3D human body prior to the optimization process. Specifically, we first estimate and refine the parameters of a parametric human body from a single image. Then during optimization, we use the posed parametric body as additional geometry constraint to regularize the diffusion model as well as the underlying density field. Lastly, we propose a UV-guided texture regularization term to further guide the completion of texture on invisible body parts. We show that ZeroAvatar significantly enhances the robustness and 3D consistency of optimization-based image-to-3D avatar generation, outperforming existing zero-shot image-to-3D methods.

Authors:Xu Bao, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Wangmeng Xiang, Jingdong Sun, Hanbing Liu, Wei Liu, Bin Luo, Yifeng Geng, Xuansong Xie

Abstract: In the realm of facial analysis, accurate landmark detection is crucial for various applications, ranging from face recognition and expression analysis to animation. Conventional heatmap or coordinate regression-based techniques, however, often face challenges in terms of computational burden and quantization errors. To address these issues, we present the KeyPoint Positioning System (KeyPosS), a groundbreaking facial landmark detection framework that stands out from existing methods. For the first time, KeyPosS employs the True-range Multilateration algorithm, a technique originally used in GPS systems, to achieve rapid and precise facial landmark detection without relying on computationally intensive regression approaches. The framework utilizes a fully convolutional network to predict a distance map, which computes the distance between a Point of Interest (POI) and multiple anchor points. These anchor points are ingeniously harnessed to triangulate the POI's position through the True-range Multilateration algorithm. Notably, the plug-and-play nature of KeyPosS enables seamless integration into any decoding stage, ensuring a versatile and adaptable solution. We conducted a thorough evaluation of KeyPosS's performance by benchmarking it against state-of-the-art models on four different datasets. The results show that KeyPosS substantially outperforms leading methods in low-resolution settings while requiring a minimal time overhead. The code is available at https://github.com/zhiqic/KeyPosS.

Authors:Geraldine Jeckeln, Selin Yavuzcan, Kate A. Marquis, Prajay Sandipkumar Mehta, Amy N. Yates, P. Jonathon Phillips

Abstract: Face recognition algorithms perform more accurately than humans in some cases, though humans and machines both show race-based accuracy differences. As algorithms continue to improve, it is important to continually assess their race bias relative to humans. We constructed a challenging test of 'cross-race' face verification and used it to compare humans and two state-of-the-art face recognition systems. Pairs of same- and different-identity faces of White and Black individuals were selected to be difficult for humans and an open-source implementation of the ArcFace face recognition algorithm from 2019 (5). Human participants (54 Black; 51 White) judged whether face pairs showed the same identity or different identities on a 7-point Likert-type scale. Two top-performing face recognition systems from the Face Recognition Vendor Test-ongoing performed the same test (7). By design, the test proved challenging for humans as a group, who performed above chance, but far less than perfect. Both state-of-the-art face recognition systems scored perfectly (no errors), consequently with equal accuracy for both races. We conclude that state-of-the-art systems for identity verification between two frontal face images of Black and White individuals can surpass the general population. Whether this result generalizes to challenging in-the-wild images is a pressing concern for deploying face recognition systems in unconstrained environments.

Authors:Adnan Munir, Abdul Jabbar Siddiqui

Abstract: To detect UAVs in real-time, computer vision and deep learning approaches are developing areas of research. There have been concerns raised regarding the possible hazards and misuse of employing unmanned aerial vehicles (UAVs) in many applications. These include potential privacy violations, safety-related issues, and security threats. Vision-based detection systems often comprise a combination of hardware components such as cameras and software components. In this work, the performance of recent and popular vision-based object detection techniques is investigated for the task of UAV detection under challenging conditions such as complex backgrounds, varying UAV sizes, complex background scenarios, and low-to-heavy rainy conditions. To study the performance of selected methods under these conditions, two datasets were curated: one with a sky background and one with complex background. In this paper, one-stage detectors and two-stage detectors are studied and evaluated. The findings presented in the paper shall help provide insights concerning the performance of the selected models for the task of UAV detection under challenging conditions and pave the way to develop more robust UAV detection methods

Authors:Jaskaran Singh Walia, Karthik Seemakurthy

Abstract: Accurately quantifying and removing submerged underwater waste plays a crucial role in safeguarding marine life and preserving the environment. While detecting floating and surface debris is relatively straightforward, quantifying submerged waste presents significant challenges due to factors like light refraction, absorption, suspended particles, and color distortion. This paper addresses these challenges by proposing the development of a custom dataset and an efficient detection approach for submerged marine debris. The dataset encompasses diverse underwater environments and incorporates annotations for precise labeling of debris instances. Ultimately, the primary objective of this custom dataset is to enhance the diversity of litter instances and improve their detection accuracy in deep submerged environments by leveraging state-of-the-art deep learning architectures.

Authors:Zhengyang Lou, Huan Xu, Fangzhou Mu, Yanli Liu, Xiaoyu Zhang, Liang Shang, Jiang Li, Bochen Guan, Yin Li, Yu Hen Hu

Abstract: Deep models have demonstrated recent success in single-image dehazing. Most prior methods consider fully supervised training and learn from paired clean and hazy images, where a hazy image is synthesized based on a clean image and its estimated depth map. This paradigm, however, can produce low-quality hazy images due to inaccurate depth estimation, resulting in poor generalization of the trained models. In this paper, we explore an alternative approach for generating paired clean-hazy images by leveraging computer graphics. Using a modern game engine, our approach renders crisp clean images and their precise depth maps, based on which high-quality hazy images can be synthesized for training dehazing models. To this end, we present SimHaze: a new synthetic haze dataset. More importantly, we show that training with SimHaze alone allows the latest dehazing models to achieve significantly better performance in comparison to previous dehazing datasets. Our dataset and code will be made publicly available.

Authors:Rawal Khirodkar, Aayush Bansal, Lingni Ma, Richard Newcombe, Minh Vo, Kris Kitani

Abstract: We present EgoHumans, a new multi-view multi-human video benchmark to advance the state-of-the-art of egocentric human 3D pose estimation and tracking. Existing egocentric benchmarks either capture single subject or indoor-only scenarios, which limit the generalization of computer vision algorithms for real-world applications. We propose a novel 3D capture setup to construct a comprehensive egocentric multi-human benchmark in the wild with annotations to support diverse tasks such as human detection, tracking, 2D/3D pose estimation, and mesh recovery. We leverage consumer-grade wearable camera-equipped glasses for the egocentric view, which enables us to capture dynamic activities like playing soccer, fencing, volleyball, etc. Furthermore, our multi-view setup generates accurate 3D ground truth even under severe or complete occlusion. The dataset consists of more than 125k egocentric images, spanning diverse scenes with a particular focus on challenging and unchoreographed multi-human activities and fast-moving egocentric views. We rigorously evaluate existing state-of-the-art methods and highlight their limitations in the egocentric scenario, specifically on multi-human tracking. To address such limitations, we propose EgoFormer, a novel approach with a multi-stream transformer architecture and explicit 3D spatial reasoning to estimate and track the human pose. EgoFormer significantly outperforms prior art by 13.6% IDF1 and 9.3 HOTA on the EgoHumans dataset.

Authors:David Azatyan

Abstract: Stroke is one of two main causes of death worldwide. Many individuals suffer from ischemic stroke every year. Only in US more over 700,000 individuals meet ischemic stroke due to blood clot blocking an artery to the brain every year. The paper describes particular approach how to apply Artificial Intelligence for purposes of separating two major acute ischemic stroke (AIS) etiology subtypes: cardiac and large artery atherosclerosis. Four deep neural network architectures and simple ensemble method are used in the approach.

Authors:Haotian Xue, Alexandre Araujo, Bin Hu, Yongxin Chen

Abstract: Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical scenarios, they often differ greatly from the actual data distribution of natural images, resulting in a trade-off between strength and stealthiness. In this paper, we propose a novel framework dubbed Diffusion-Based Projected Gradient Descent (Diff-PGD) for generating realistic adversarial samples. By exploiting a gradient guided by a diffusion model, Diff-PGD ensures that adversarial samples remain close to the original data distribution while maintaining their effectiveness. Moreover, our framework can be easily customized for specific tasks such as digital attacks, physical-world attacks, and style-based attacks. Compared with existing methods for generating natural-style adversarial samples, our framework enables the separation of optimizing adversarial loss from other surrogate losses (e.g., content/smoothness/style loss), making it more stable and controllable. Finally, we demonstrate that the samples generated using Diff-PGD have better transferability and anti-purification power than traditional gradient-based methods. Code will be released in https://github.com/xavihart/Diff-PGD

Authors:Daniel Schug, Sai Yerramreddy, Rich Caruana, Craig Greenberg, Justyna P. Zwolak

Abstract: As the deployment of computer vision technology becomes increasingly common in applications of consequence such as medicine or science, the need for explanations of the system output has become a focus of great concern. Unfortunately, many state-of-the-art computer vision models are opaque, making their use challenging from an explanation standpoint, and current approaches to explaining these opaque models have stark limitations and have been the subject of serious criticism. In contrast, Explainable Boosting Machines (EBMs) are a class of models that are easy to interpret and achieve performance on par with the very best-performing models, however, to date EBMs have been limited solely to tabular data. Driven by the pressing need for interpretable models in science, we propose the use of EBMs for scientific image data. Inspired by an important application underpinning the development of quantum technologies, we apply EBMs to cold-atom soliton image data, and, in doing so, demonstrate EBMs for image data for the first time. To tabularize the image data we employ Gabor Wavelet Transform-based techniques that preserve the spatial structure of the data. We show that our approach provides better explanations than other state-of-the-art explainability methods for images.

Authors:Hao Chen, Haotian Zhang, Keyan Chen, Chenyao Zhou, Song Chen, Zhengxia Zhou, Zhenwei Shi

Abstract: Most contemporary supervised Remote Sensing (RS) image Change Detection (CD) approaches are customized for equal-resolution bitemporal images. Real-world applications raise the need for cross-resolution change detection, aka, CD based on bitemporal images with different spatial resolutions. Current cross-resolution methods that are trained with samples of a fixed resolution difference (resolution ratio between the high-resolution (HR) image and the low-resolution (LR) one) may fit a certain ratio but lack adaptation to other resolution differences. Toward continuous cross-resolution CD, we propose scale-invariant learning to enforce the model consistently predicting HR results given synthesized samples of varying bitemporal resolution differences. Concretely, we synthesize blurred versions of the HR image by random downsampled reconstructions to reduce the gap between HR and LR images. We introduce coordinate-based representations to decode per-pixel predictions by feeding the coordinate query and corresponding multi-level embedding features into an MLP that implicitly learns the shape of land cover changes, therefore benefiting recognizing blurred objects in the LR image. Moreover, considering that spatial resolution mainly affects the local textures, we apply local-window self-attention to align bitemporal features during the early stages of the encoder. Extensive experiments on two synthesized and one real-world different-resolution CD datasets verify the effectiveness of the proposed method. Our method significantly outperforms several vanilla CD methods and two cross-resolution CD methods on the three datasets both in in-distribution and out-of-distribution settings. The empirical results suggest that our method could yield relatively consistent HR change predictions regardless of varying resolution difference ratios. Our code will be public.

Authors:Junrui Xiao, Zhikai Li, Lianwei Yang, Qingyi Gu

Abstract: Vision Transformers (ViTs) have emerged as the fundamental architecture for most computer vision fields, but the considerable memory and computation costs hinders their application on resource-limited devices. As one of the most powerful compression methods, binarization reduces the computation of the neural network by quantizing the weights and activation values as $\pm$1. Although existing binarization methods have demonstrated excellent performance on Convolutional Neural Networks (CNNs), the full binarization of ViTs is still under-studied and suffering a significant performance drop. In this paper, we first argue empirically that the severe performance degradation is mainly caused by the weight oscillation in the binarization training and the information distortion in the activation of ViTs. Based on these analyses, we propose $\textbf{BinaryViT}$, an accurate full binarization scheme for ViTs, which pushes the quantization of ViTs to the limit. Specifically, we propose a novel gradient regularization scheme (GRS) for driving a bimodal distribution of the weights to reduce oscillation in binarization training. Moreover, we design an activation shift module (ASM) to adaptively tune the activation distribution to reduce the information distortion caused by binarization. Extensive experiments on ImageNet dataset show that our BinaryViT consistently surpasses the strong baseline by 2.05% and improve the accuracy of fully binarized ViTs to a usable level. Furthermore, our method achieves impressive savings of 16.2$\times$ and 17.7$\times$ in model size and OPs compared to the full-precision DeiT-S. The codes and models will be released on github.

Authors:Peyman Gholami, Robert Xiao

Abstract: Depth cameras have found applications in diverse fields, such as computer vision, artificial intelligence, and video gaming. However, the high latency and low frame rate of existing commodity depth cameras impose limitations on their applications. We propose a fast and accurate depth map reconstruction technique to reduce latency and increase the frame rate in depth cameras. Our approach uses only a commodity depth camera and color camera in a hybrid camera setup; our prototype is implemented using a Kinect Azure depth camera at 30 fps and a high-speed RGB iPhone 11 Pro camera captured at 240 fps. The proposed network, AutoDepthNet, is an encoder-decoder model that captures frames from the high-speed RGB camera and combines them with previous depth frames to reconstruct a stream of high frame rate depth maps. On GPU, with a 480 x 270 output resolution, our system achieves an inference time of 8 ms, enabling real-time use at up to 200 fps with parallel processing. AutoDepthNet can estimate depth values with an average RMS error of 0.076, a 44.5% improvement compared to an optical flow-based comparison method. Our method can also improve depth map quality by estimating depth values for missing and invalidated pixels. The proposed method can be easily applied to existing depth cameras and facilitates the use of depth cameras in applications that require high-speed depth estimation. We also showcase the effectiveness of the framework in upsampling different sparse datasets e.g. video object segmentation. As a demonstration of our method, we integrated our framework into existing body tracking systems and demonstrated the robustness of the proposed method in such applications.

Authors:Dongxu Yue, Qin Guo, Munan Ning, Jiaxi Cui, Yuesheng Zhu, Li Yuan

Abstract: Editing real facial images is a crucial task in computer vision with significant demand in various real-world applications. While GAN-based methods have showed potential in manipulating images especially when combined with CLIP, these methods are limited in their ability to reconstruct real images due to challenging GAN inversion capability. Despite the successful image reconstruction achieved by diffusion-based methods, there are still challenges in effectively manipulating fine-gained facial attributes with textual instructions.To address these issues and facilitate convenient manipulation of real facial images, we propose a novel approach that conduct text-driven image editing in the semantic latent space of diffusion model. By aligning the temporal feature of the diffusion model with the semantic condition at generative process, we introduce a stable manipulation strategy, which perform precise zero-shot manipulation effectively. Furthermore, we develop an interactive system named ChatFace, which combines the zero-shot reasoning ability of large language models to perform efficient manipulations in diffusion semantic latent space. This system enables users to perform complex multi-attribute manipulations through dialogue, opening up new possibilities for interactive image editing. Extensive experiments confirmed that our approach outperforms previous methods and enables precise editing of real facial images, making it a promising candidate for real-world applications. Project page: https://dongxuyue.github.io/chatface/

Authors:Yi-Zhan Xu, Chih-Yao Chen, Cheng-Te Li

Abstract: Unsupervised learning has grown in popularity because of the difficulty of collecting annotated data and the development of modern frameworks that allow us to learn from unlabeled data. Existing studies, however, either disregard variations at different levels of similarity or only consider negative samples from one batch. We argue that image pairs should have varying degrees of similarity, and the negative samples should be allowed to be drawn from the entire dataset. In this work, we propose Search-based Unsupervised Visual Representation Learning (SUVR) to learn better image representations in an unsupervised manner. We first construct a graph from the image dataset by the similarity between images, and adopt the concept of graph traversal to explore positive samples. In the meantime, we make sure that negative samples can be drawn from the full dataset. Quantitative experiments on five benchmark image classification datasets demonstrate that SUVR can significantly outperform strong competing methods on unsupervised embedding learning. Qualitative experiments also show that SUVR can produce better representations in which similar images are clustered closer together than unrelated images in the latent space.

Authors:Tianlun Zheng, Zhineng Chen, BingChen Huang, Wei Zhang, Yu-Gang Jiang

Abstract: Traditional Multilingual Text Recognition (MLTR) usually targets a fixed set of languages and thus struggles to handle newly added languages or adapt to ever-changing class distributions. In this paper, we introduce the Incremental Multilingual Text Recognition (IMLTR) task in the incremental learning setting, where new language data comes in batches. Compared to generic incremental learning, IMLTR is even more challenging as it suffers from rehearsal-imbalance (uneven distribution of sample characters in the rehearsal set). To address this issue, we propose a Multiplexed Routing Network (MRN), where a series of recognizers is trained for each language. Subsequently, a language predictor is adopted to weigh the recognizers for voting. Since the recognizers are derived from the original model, MRN effectively reduces the reliance on older data and is better suited for rehearsal-imbalance. We extensively evaluate MRN on MLT17 and MLT19 datasets, outperforming existing state-of-the-art methods by a large margin, i.e., accuracy improvement ranging from 10.3% to 27.4% under different settings.

Authors:Zhengkai Jiang, Liang Liu, Jiangning Zhang, Yabiao Wang, Mingang Chen, Chengjie Wang

Abstract: This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective. The dual attention mechanism consists of two parallel components: local attention generated by Convolutional Neural Networks (CNNs) and long-range attention generated by Vision Transformers (ViTs). To address the high computational complexity and memory footprint of vanilla Multi-Head Self-Attention (MHSA), we introduce a novel Multi-Head Partition-wise Attention (MHPA) mechanism. The partition-wise attention approach models both intra-partition and inter-partition attention simultaneously. Building on the dual attention block and partition-wise attention mechanism, we present a hierarchical vision backbone called DualFormer. We evaluate the effectiveness of our model on several computer vision tasks, including image classification on ImageNet, object detection on COCO, and semantic segmentation on Cityscapes. Specifically, the proposed DualFormer-XS achieves 81.5\% top-1 accuracy on ImageNet, outperforming the recent state-of-the-art MPViT-XS by 0.6\% top-1 accuracy with much higher throughput.

Authors:Jaemoo Choi, Jaewoong Choi, Myungjoo Kang

Abstract: Optimal Transport (OT) problem investigates a transport map that bridges two distributions while minimizing a given cost function. In this regard, OT between tractable prior distribution and data has been utilized for generative modeling tasks. However, OT-based methods are susceptible to outliers and face optimization challenges during training. In this paper, we propose a novel generative model based on the semi-dual formulation of Unbalanced Optimal Transport (UOT). Unlike OT, UOT relaxes the hard constraint on distribution matching. This approach provides better robustness against outliers, stability during training, and faster convergence. We validate these properties empirically through experiments. Moreover, we study the theoretical upper-bound of divergence between distributions in UOT. Our model outperforms existing OT-based generative models, achieving FID scores of 2.97 on CIFAR-10 and 5.80 on CelebA-HQ-256.

Authors:Nikita Srivatsan, Sofia Samaniego, Omar Florez, Taylor Berg-Kirkpatrick

Abstract: In this work we present an approach for generating alternative text (or alt-text) descriptions for images shared on social media, specifically Twitter. This task is more than just a special case of image captioning, as alt-text is both more literally descriptive and context-specific. Also critically, images posted to Twitter are often accompanied by user-written text that despite not necessarily describing the image may provide useful context that if properly leveraged can be informative -- e.g. the tweet may name an uncommon object in the image that the model has not previously seen. We address this with a CLIP prefix model that extracts an embedding of the image and passes it to a mapping network that outputs a short sequence in word embedding space, or a ``prefix'', to which we also concatenate the text from the tweet itself. This lets the model condition on both visual and textual information from the post. The combined multimodal prefix is then fed as a prompt to a pretrained language model which autoregressively completes the sequence to generate the alt-text. While prior work has used similar methods for captioning, ours is the first to our knowledge that incorporates textual information from the associated social media post into the prefix as well, and we further demonstrate through ablations that utility of these two information sources stacks. We put forward a new dataset scraped from Twitter and evaluate on it across a variety of automated metrics as well as human evaluation, and show that our approach of conditioning on both tweet text and visual information significantly outperforms prior work.

Authors:Michael Baltaxe, Tomer Pe'er, Dan Levi

Abstract: Autonomous driving and advanced driver-assistance systems rely on a set of sensors and algorithms to perform the appropriate actions and provide alerts as a function of the driving scene. Typically, the sensors include color cameras, radar, lidar and ultrasonic sensors. Strikingly however, although light polarization is a fundamental property of light, it is seldom harnessed for perception tasks. In this work we analyze the potential for improvement in perception tasks when using an RGB-polarimetric camera, as compared to an RGB camera. We examine monocular depth estimation and free space detection during the middle of the day, when polarization is independent of subject heading, and show that a quantifiable improvement can be achieved for both of them using state-of-the-art deep neural networks, with a minimum of architectural changes. We also present a new dataset composed of RGB-polarimetric images, lidar scans, GNSS / IMU readings and free space segmentations that further supports developing perception algorithms that take advantage of light polarization.

Authors:Xu Yang, Yongliang Wu, Mingzhuo Yang, Haokun Chen

Abstract: After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest way, \ie, randomly sampling, to configure in-context image-text pairs. In order to explore the effects of varying configurations on VL in-context learning, we devised four strategies for image selection and four for caption assignment to configure in-context image-text pairs for image captioning. Here Image Captioning is used as the case study since it can be seen as the visually-conditioned LM. Our comprehensive experiments yield two counter-intuitive but valuable insights, highlighting the distinct characteristics of VL in-context learning due to multi-modal synergy, as compared to the NLP case.

Authors:Yuhang Zang, Kaiyang Zhou, Chen Huang, Chen Change Loy

Abstract: This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detector called CascadeMatch. Our detector features a cascade network architecture, which has multi-stage detection heads with progressive confidence thresholds. To avoid manually tuning the thresholds, we design a new adaptive pseudo-label mining mechanism to automatically identify suitable values from data. To mitigate confirmation bias, where a model is negatively reinforced by incorrect pseudo-labels produced by itself, each detection head is trained by the ensemble pseudo-labels of all detection heads. Experiments on two long-tailed datasets, i.e., LVIS and COCO-LT, demonstrate that CascadeMatch surpasses existing state-of-the-art semi-supervised approaches -- across a wide range of detection architectures -- in handling long-tailed object detection. For instance, CascadeMatch outperforms Unbiased Teacher by 1.9 AP Fix on LVIS when using a ResNet50-based Cascade R-CNN structure, and by 1.7 AP Fix when using Sparse R-CNN with a Transformer encoder. We also show that CascadeMatch can even handle the challenging sparsely annotated object detection problem.

Authors:Shiva Raj Pokhrel, Jonathan Kua, Deol Satish, Phil Williams, Arkady Zaslavsky, Seng W. Loke, Jinho Choi

Abstract: In this work, we propose and develop a simple experimental testbed to study the feasibility of a novel idea by coupling radio frequency (RF) sensing technology with Correlated Knowledge Distillation (CKD) theory towards designing lightweight, near real-time and precise human pose monitoring systems. The proposed CKD framework transfers and fuses pose knowledge from a robust "Teacher" model to a parameterized "Student" model, which can be a promising technique for obtaining accurate yet lightweight pose estimates. To assure its efficacy, we implemented CKD for distilling logits in our integrated Software Defined Radio (SDR)-based experimental setup and investigated the RF-visual signal correlation. Our CKD-RF sensing technique is characterized by two modes -- a camera-fed Teacher Class Network (e.g., images, videos) with an SDR-fed Student Class Network (e.g., RF signals). Specifically, our CKD model trains a dual multi-branch teacher and student network by distilling and fusing knowledge bases. The resulting CKD models are then subsequently used to identify the multimodal correlation and teach the student branch in reverse. Instead of simply aggregating their learnings, CKD training comprised multiple parallel transformations with the two domains, i.e., visual images and RF signals. Once trained, our CKD model can efficiently preserve privacy and utilize the multimodal correlated logits from the two different neural networks for estimating poses without using visual signals/video frames (by using only the RF signals).

Authors:Zhiwen Yan, Chen Li, Gim Hee Lee

Abstract: Dynamic neural radiance fields (dynamic NeRFs) have demonstrated impressive results in novel view synthesis on 3D dynamic scenes. However, they often require complete video sequences for training followed by novel view synthesis, which is similar to playing back the recording of a dynamic 3D scene. In contrast, we propose OD-NeRF to efficiently train and render dynamic NeRFs on-the-fly which instead is capable of streaming the dynamic scene. When training on-the-fly, the training frames become available sequentially and the model is trained and rendered frame-by-frame. The key challenge of efficient on-the-fly training is how to utilize the radiance field estimated from the previous frames effectively. To tackle this challenge, we propose: 1) a NeRF model conditioned on the multi-view projected colors to implicitly track correspondence between the current and previous frames, and 2) a transition and update algorithm that leverages the occupancy grid from the last frame to sample efficiently at the current frame. Our algorithm can achieve an interactive speed of 6FPS training and rendering on synthetic dynamic scenes on-the-fly, and a significant speed-up compared to the state-of-the-art on real-world dynamic scenes.

Authors:Tianwen Qian, Jingjing Chen, Linhai Zhuo, Yang Jiao, Yu-Gang Jiang

Abstract: We introduce a novel visual question answering (VQA) task in the context of autonomous driving, aiming to answer natural language questions based on street-view clues. Compared to traditional VQA tasks, VQA in autonomous driving scenario presents more challenges. Firstly, the raw visual data are multi-modal, including images and point clouds captured by camera and LiDAR, respectively. Secondly, the data are multi-frame due to the continuous, real-time acquisition. Thirdly, the outdoor scenes exhibit both moving foreground and static background. Existing VQA benchmarks fail to adequately address these complexities. To bridge this gap, we propose NuScenes-QA, the first benchmark for VQA in the autonomous driving scenario, encompassing 34K visual scenes and 460K question-answer pairs. Specifically, we leverage existing 3D detection annotations to generate scene graphs and design question templates manually. Subsequently, the question-answer pairs are generated programmatically based on these templates. Comprehensive statistics prove that our NuScenes-QA is a balanced large-scale benchmark with diverse question formats. Built upon it, we develop a series of baselines that employ advanced 3D detection and VQA techniques. Our extensive experiments highlight the challenges posed by this new task. Codes and dataset are available at https://github.com/qiantianwen/NuScenes-QA.

Authors:Hong Wang, Su Yang, Xiaoke Huang, Weishan Zhang

Abstract: Token filtering to reduce irrelevant tokens prior to self-attention is a straightforward way to enable efficient vision Transformer. This is the first work to view token filtering from a feature selection perspective, where we weigh the importance of a token according to how much it can change the loss once masked. If the loss changes greatly after masking a token of interest, it means that such a token has a significant impact on the final decision and is thus relevant. Otherwise, the token is less important for the final decision, so it can be filtered out. After applying the token filtering module generalized from the whole training data, the token number fed to the self-attention module can be obviously reduced in the inference phase, leading to much fewer computations in all the subsequent self-attention layers. The token filter can be realized using a very simple network, where we utilize multi-layer perceptron. Except for the uniqueness of performing token filtering only once from the very beginning prior to self-attention, the other core feature making our method different from the other token filters lies in the predictability of token impact from a feature selection point of view. The experiments show that the proposed method provides an efficient way to approach a light weighted model after optimized with a backbone by means of fine tune, which is easy to be deployed in comparison with the existing methods based on training from scratch.

Authors:Junyoung Byun, Myung-Joon Kwon, Seungju Cho, Yoonji Kim, Changick Kim

Abstract: Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications. These adversarial examples tend to be transferable between models, but targeted attacks still have lower attack success rates due to significant variations in decision boundaries. To enhance the transferability of targeted adversarial examples, we propose introducing competition into the optimization process. Our idea is to craft adversarial perturbations in the presence of two new types of competitor noises: adversarial perturbations towards different target classes and friendly perturbations towards the correct class. With these competitors, even if an adversarial example deceives a network to extract specific features leading to the target class, this disturbance can be suppressed by other competitors. Therefore, within this competition, adversarial examples should take different attack strategies by leveraging more diverse features to overwhelm their interference, leading to improving their transferability to different models. Considering the computational complexity, we efficiently simulate various interference from these two types of competitors in feature space by randomly mixing up stored clean features in the model inference and named this method Clean Feature Mixup (CFM). Our extensive experimental results on the ImageNet-Compatible and CIFAR-10 datasets show that the proposed method outperforms the existing baselines with a clear margin. Our code is available at https://github.com/dreamflake/CFM.

Authors:Taesun Yeom, Minhyeok Lee

Abstract: Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as mode collapse, training instability, and low-quality output in cases of datasets with high intra-class variation. Furthermore, most GANs often converge in larger iterations, resulting in poor iteration efficacy in training procedures. While Diffusion-GAN has shown potential in generating realistic samples, it has a critical limitation in generating class-conditional samples. To overcome these limitations, we propose a novel approach for class-conditional image generation using GANs called DuDGAN, which incorporates a dual diffusion-based noise injection process. Our method consists of three unique networks: a discriminator, a generator, and a classifier. During the training process, Gaussian-mixture noises are injected into the two noise-aware networks, the discriminator and the classifier, in distinct ways. This noisy data helps to prevent overfitting by gradually introducing more challenging tasks, leading to improved model performance. As a result, our method outperforms state-of-the-art conditional GAN models for image generation in terms of performance. We evaluated our method using the AFHQ, Food-101, and CIFAR-10 datasets and observed superior results across metrics such as FID, KID, Precision, and Recall score compared with comparison models, highlighting the effectiveness of our approach.

Authors:Žiga Babnik, Naser Damer, Vitomir Štruc

Abstract: Contemporary face recognition (FR) models achieve near-ideal recognition performance in constrained settings, yet do not fully translate the performance to unconstrained (realworld) scenarios. To help improve the performance and stability of FR systems in such unconstrained settings, face image quality assessment (FIQA) techniques try to infer sample-quality information from the input face images that can aid with the recognition process. While existing FIQA techniques are able to efficiently capture the differences between high and low quality images, they typically cannot fully distinguish between images of similar quality, leading to lower performance in many scenarios. To address this issue, we present in this paper a supervised quality-label optimization approach, aimed at improving the performance of existing FIQA techniques. The developed optimization procedure infuses additional information (computed with a selected FR model) into the initial quality scores generated with a given FIQA technique to produce better estimates of the "actual" image quality. We evaluate the proposed approach in comprehensive experiments with six state-of-the-art FIQA approaches (CR-FIQA, FaceQAN, SER-FIQ, PCNet, MagFace, SDD-FIQA) on five commonly used benchmarks (LFW, CFPFP, CPLFW, CALFW, XQLFW) using three targeted FR models (ArcFace, ElasticFace, CurricularFace) with highly encouraging results.

Authors:Shuting Yan, Pingping Chen, Honghui Chen, Huan Mao, Feng Chen, Zhijian Lin

Abstract: Anomaly detection is represented as an unsupervised learning to identify deviated images from normal images. In general, there are two main challenges of anomaly detection tasks, i.e., the class imbalance and the unexpectedness of anomalies. In this paper, we propose a multiresolution feature guidance method based on Transformer named GTrans for unsupervised anomaly detection and localization. In GTrans, an Anomaly Guided Network (AGN) pre-trained on ImageNet is developed to provide surrogate labels for features and tokens. Under the tacit knowledge guidance of the AGN, the anomaly detection network named Trans utilizes Transformer to effectively establish a relationship between features with multiresolution, enhancing the ability of the Trans in fitting the normal data manifold. Due to the strong generalization ability of AGN, GTrans locates anomalies by comparing the differences in spatial distance and direction of multi-scale features extracted from the AGN and the Trans. Our experiments demonstrate that the proposed GTrans achieves state-of-the-art performance in both detection and localization on the MVTec AD dataset. GTrans achieves image-level and pixel-level anomaly detection AUROC scores of 99.0% and 97.9% on the MVTec AD dataset, respectively.

Authors:Chuhao Liu, Shaojie Shen

Abstract: Loop detection plays a key role in visual Simultaneous Localization and Mapping (SLAM) by correcting the accumulated pose drift. In indoor scenarios, the richly distributed semantic landmarks are view-point invariant and hold strong descriptive power in loop detection. The current semantic-aided loop detection embeds the topology between semantic instances to search a loop. However, current semantic-aided loop detection methods face challenges in dealing with ambiguous semantic instances and drastic viewpoint differences, which are not fully addressed in the literature. This paper introduces a novel loop detection method based on an incrementally created scene graph, targeting the visual SLAM at indoor scenes. It jointly considers the macro-view topology, micro-view topology, and occupancy of semantic instances to find correct correspondences. Experiments using handheld RGB-D sequence show our method is able to accurately detect loops in drastically changed viewpoints. It maintains a high precision in observing objects with similar topology and appearance. Our method also demonstrates that it is robust in changed indoor scenes.

Authors:Arne F. Nix, Max F. Burg, Fabian H. Sinz

Abstract: Knowledge distillation (KD) is a simple and successful method to transfer knowledge from a teacher to a student model solely based on functional activity. However, current KD has a few shortcomings: it has recently been shown that this method is unsuitable to transfer simple inductive biases like shift equivariance, struggles to transfer out of domain generalization, and optimization time is magnitudes longer compared to default non-KD model training. To improve these aspects of KD, we propose Hard Augmentations for Robust Distillation (HARD), a generally applicable data augmentation framework, that generates synthetic data points for which the teacher and the student disagree. We show in a simple toy example that our augmentation framework solves the problem of transferring simple equivariances with KD. We then apply our framework in real-world tasks for a variety of augmentation models, ranging from simple spatial transformations to unconstrained image manipulations with a pretrained variational autoencoder. We find that our learned augmentations significantly improve KD performance on in-domain and out-of-domain evaluation. Moreover, our method outperforms even state-of-the-art data augmentations and since the augmented training inputs can be visualized, they offer a qualitative insight into the properties that are transferred from the teacher to the student. Thus HARD represents a generally applicable, dynamically optimized data augmentation technique tailored to improve the generalization and convergence speed of models trained with KD.

Authors:Zhitong Xiong, Sining Chen, Yi Wang, Lichao Mou, Xiao Xiang Zhu

Abstract: Geometric information in the normalized digital surface models (nDSM) is highly correlated with the semantic class of the land cover. Exploiting two modalities (RGB and nDSM (height)) jointly has great potential to improve the segmentation performance. However, it is still an under-explored field in remote sensing due to the following challenges. First, the scales of existing datasets are relatively small and the diversity of existing datasets is limited, which restricts the ability of validation. Second, there is a lack of unified benchmarks for performance assessment, which leads to difficulties in comparing the effectiveness of different models. Last, sophisticated multi-modal semantic segmentation methods have not been deeply explored for remote sensing data. To cope with these challenges, in this paper, we introduce a new remote-sensing benchmark dataset for multi-modal semantic segmentation based on RGB-Height (RGB-H) data. Towards a fair and comprehensive analysis of existing methods, the proposed benchmark consists of 1) a large-scale dataset including co-registered RGB and nDSM pairs and pixel-wise semantic labels; 2) a comprehensive evaluation and analysis of existing multi-modal fusion strategies for both convolutional and Transformer-based networks on remote sensing data. Furthermore, we propose a novel and effective Transformer-based intermediary multi-modal fusion (TIMF) module to improve the semantic segmentation performance through adaptive token-level multi-modal fusion.The designed benchmark can foster future research on developing new methods for multi-modal learning on remote sensing data. Extensive analyses of those methods are conducted and valuable insights are provided through the experimental results. Code for the benchmark and baselines can be accessed at \url{https://github.com/EarthNets/RSI-MMSegmentation}.

Authors:Xingxing Zuo, Nan Yang, Nathaniel Merrill, Binbin Xu, Stefan Leutenegger

Abstract: Incrementally recovering 3D dense structures from monocular videos is of paramount importance since it enables various robotics and AR applications. Feature volumes have recently been shown to enable efficient and accurate incremental dense reconstruction without the need to first estimate depth, but they are not able to achieve as high of a resolution as depth-based methods due to the large memory consumption of high-resolution feature volumes. This letter proposes a real-time feature volume-based dense reconstruction method that predicts TSDF (Truncated Signed Distance Function) values from a novel sparsified deep feature volume, which is able to achieve higher resolutions than previous feature volume-based methods, and is favorable in large-scale outdoor scenarios where the majority of voxels are empty. An uncertainty-aware multi-view stereo (MVS) network is leveraged to infer initial voxel locations of the physical surface in a sparse feature volume. Then for refining the recovered 3D geometry, deep features are attentively aggregated from multiview images at potential surface locations, and temporally fused. Besides achieving higher resolutions than before, our method is shown to produce more complete reconstructions with finer detail in many cases. Extensive evaluations on both public and self-collected datasets demonstrate a very competitive real-time reconstruction result for our method compared to state-of-the-art reconstruction methods in both indoor and outdoor settings.

Authors:Jue Liu, Feipeng Da

Abstract: 3D pose transfer solves the problem of additional input and correspondence of traditional deformation transfer, only the source and target meshes need to be input, and the pose of the source mesh can be transferred to the target mesh. Some lightweight methods proposed in recent years consume less memory but cause spikes and distortions for some unseen poses, while others are costly in training due to the inclusion of large matrix multiplication and adversarial networks. In addition, the meshes with different numbers of vertices also increase the difficulty of pose transfer. In this work, we propose a Dual-Side Feature Fusion Pose Transfer Network to improve the pose transfer accuracy of the lightweight method. Our method takes the pose features as one of the side inputs to the decoding network and fuses them into the target mesh layer by layer at multiple scales. Our proposed Feature Fusion Adaptive Instance Normalization has the characteristic of having two side input channels that fuse pose features and identity features as denormalization parameters, thus enhancing the pose transfer capability of the network. Extensive experimental results show that our proposed method has stronger pose transfer capability than state-of-the-art methods while maintaining a lightweight network structure, and can converge faster.

Authors:Jiayi Zhu, Xuebin Qin, Abdulmotaleb Elsaddik

Abstract: In this paper, we introduce Divide-and-Conquer into the salient object detection (SOD) task to enable the model to learn prior knowledge that is for predicting the saliency map. We design a novel network, Divide-and-Conquer Network (DC-Net) which uses two encoders to solve different subtasks that are conducive to predicting the final saliency map, here is to predict the edge maps with width 4 and location maps of salient objects and then aggregate the feature maps with different semantic information into the decoder to predict the final saliency map. The decoder of DC-Net consists of our newly designed two-level Residual nested-ASPP (ResASPP$^{2}$) modules, which have the ability to capture a large number of different scale features with a small number of convolution operations and have the advantages of maintaining high resolution all the time and being able to obtain a large and compact effective receptive field (ERF). Based on the advantage of Divide-and-Conquer's parallel computing, we use Parallel Acceleration to speed up DC-Net, allowing it to achieve competitive performance on six LR-SOD and five HR-SOD datasets under high efficiency (60 FPS and 55 FPS). Codes and results are available: https://github.com/PiggyJerry/DC-Net.

Authors:Christoph Auer, Ahmed Nassar, Maksym Lysak, Michele Dolfi, Nikolaos Livathinos, Peter Staar

Abstract: Transforming documents into machine-processable representations is a challenging task due to their complex structures and variability in formats. Recovering the layout structure and content from PDF files or scanned material has remained a key problem for decades. ICDAR has a long tradition in hosting competitions to benchmark the state-of-the-art and encourage the development of novel solutions to document layout understanding. In this report, we present the results of our \textit{ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents}, which posed the challenge to accurately segment the page layout in a broad range of document styles and domains, including corporate reports, technical literature and patents. To raise the bar over previous competitions, we engineered a hard competition dataset and proposed the recent DocLayNet dataset for training. We recorded 45 team registrations and received official submissions from 21 teams. In the presented solutions, we recognize interesting combinations of recent computer vision models, data augmentation strategies and ensemble methods to achieve remarkable accuracy in the task we posed. A clear trend towards adoption of vision-transformer based methods is evident. The results demonstrate substantial progress towards achieving robust and highly generalizing methods for document layout understanding.

Authors:Yichen Yan, Xingjian He, Wenxuan Wan, Jing Liu

Abstract: Referring image segmentation aims to segment an object referred to by natural language expression from an image. However, this task is challenging due to the distinct data properties between text and image, and the randomness introduced by diverse objects and unrestricted language expression. Most of previous work focus on improving cross-modal feature fusion while not fully addressing the inherent uncertainty caused by diverse objects and unrestricted language. To tackle these problems, we propose an end-to-end Multi-Mask Network for referring image segmentation(MMNet). we first combine picture and language and then employ an attention mechanism to generate multiple queries that represent different aspects of the language expression. We then utilize these queries to produce a series of corresponding segmentation masks, assigning a score to each mask that reflects its importance. The final result is obtained through the weighted sum of all masks, which greatly reduces the randomness of the language expression. Our proposed framework demonstrates superior performance compared to state-of-the-art approaches on the two most commonly used datasets, RefCOCO, RefCOCO+ and G-Ref, without the need for any post-processing. This further validates the efficacy of our proposed framework.

Authors:Florian Heidecker, Ahmad El-Khateeb, Bernhard Sick

Abstract: The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.

Authors:Gabriel Kasmi, Laurent Dubus, Yves-Marie Saint Drenan, Philippe Blanc

Abstract: Neural networks have shown remarkable performance in computer vision, but their deployment in real-world scenarios is challenging due to their sensitivity to image corruptions. Existing attribution methods are uninformative for explaining the sensitivity to image corruptions, while the literature on robustness only provides model-based explanations. However, the ability to scrutinize models' behavior under image corruptions is crucial to increase the user's trust. Towards this end, we introduce the Wavelet sCale Attribution Method (WCAM), a generalization of attribution from the pixel domain to the space-scale domain. Attribution in the space-scale domain reveals where and on what scales the model focuses. We show that the WCAM explains models' failures under image corruptions, identifies sufficient information for prediction, and explains how zoom-in increases accuracy.

Authors:Haoxuan You, Rui Sun, Zhecan Wang, Long Chen, Gengyu Wang, Hammad A. Ayyubi, Kai-Wei Chang, Shih-Fu Chang

Abstract: The field of vision-and-language (VL) understanding has made unprecedented progress with end-to-end large pre-trained VL models (VLMs). However, they still fall short in zero-shot reasoning tasks that require multi-step inferencing. To achieve this goal, previous works resort to a divide-and-conquer pipeline. In this paper, we argue that previous efforts have several inherent shortcomings: 1) They rely on domain-specific sub-question decomposing models. 2) They force models to predict the final answer even if the sub-questions or sub-answers provide insufficient information. We address these limitations via IdealGPT, a framework that iteratively decomposes VL reasoning using large language models (LLMs). Specifically, IdealGPT utilizes an LLM to generate sub-questions, a VLM to provide corresponding sub-answers, and another LLM to reason to achieve the final answer. These three modules perform the divide-and-conquer procedure iteratively until the model is confident about the final answer to the main question. We evaluate IdealGPT on multiple challenging VL reasoning tasks under a zero-shot setting. In particular, our IdealGPT outperforms the best existing GPT-4-like models by an absolute 10% on VCR and 15% on SNLI-VE. Code is available at https://github.com/Hxyou/IdealGPT

Authors:Daniel Reich, Felix Putze, Tanja Schultz

Abstract: Metrics for Visual Grounding (VG) in Visual Question Answering (VQA) systems primarily aim to measure a system's reliance on relevant parts of the image when inferring an answer to the given question. Lack of VG has been a common problem among state-of-the-art VQA systems and can manifest in over-reliance on irrelevant image parts or a disregard for the visual modality entirely. Although inference capabilities of VQA models are often illustrated by a few qualitative illustrations, most systems are not quantitatively assessed for their VG properties. We believe, an easily calculated criterion for meaningfully measuring a system's VG can help remedy this shortcoming, as well as add another valuable dimension to model evaluations and analysis. To this end, we propose a new VG metric that captures if a model a) identifies question-relevant objects in the scene, and b) actually relies on the information contained in the relevant objects when producing its answer, i.e., if its visual grounding is both "faithful" and "plausible". Our metric, called "Faithful and Plausible Visual Grounding" (FPVG), is straightforward to determine for most VQA model designs. We give a detailed description of FPVG and evaluate several reference systems spanning various VQA architectures. Code to support the metric calculations on the GQA data set is available on GitHub.

Authors:Gen Luo, Yiyi Zhou, Tianhe Ren, Shengxin Chen, Xiaoshuai Sun, Rongrong Ji

Abstract: Recently, growing interest has been aroused in extending the multimodal capability of large language models (LLMs), e.g., vision-language (VL) learning, which is regarded as the next milestone of artificial general intelligence. However, existing solutions are prohibitively expensive, which not only need to optimize excessive parameters, but also require another large-scale pre-training before VL instruction tuning. In this paper, we propose a novel and affordable solution for the effective VL adaption of LLMs, called Mixture-of-Modality Adaptation (MMA). Instead of using large neural networks to connect the image encoder and LLM, MMA adopts lightweight modules, i.e., adapters, to bridge the gap between LLMs and VL tasks, which also enables the joint optimization of the image and language models. Meanwhile, MMA is also equipped with a routing algorithm to help LLMs achieve an automatic shift between single- and multi-modal instructions without compromising their ability of natural language understanding. To validate MMA, we apply it to a recent LLM called LLaMA and term this formed large vision-language instructed model as LaVIN. To validate MMA and LaVIN, we conduct extensive experiments under two setups, namely multimodal science question answering and multimodal dialogue. The experimental results not only demonstrate the competitive performance and the superior training efficiency of LaVIN than existing multimodal LLMs, but also confirm its great potential as a general-purpose chatbot. More importantly, the actual expenditure of LaVIN is extremely cheap, e.g., only 1.4 training hours with 3.8M trainable parameters, greatly confirming the effectiveness of MMA. Our project is released at https://luogen1996.github.io/lavin.

Authors:Rodrigo Valerio, Joao Bordalo, Michal Yarom, Yonattan Bitton, Idan Szpektor, Joao Magalhaes

Abstract: Text to image generation methods (T2I) are widely popular in generating art and other creative artifacts. While visual hallucinations can be a positive factor in scenarios where creativity is appreciated, such artifacts are poorly suited for cases where the generated image needs to be grounded in complex natural language without explicit visual elements. In this paper, we propose to strengthen the consistency property of T2I methods in the presence of natural complex language, which often breaks the limits of T2I methods by including non-visual information, and textual elements that require knowledge for accurate generation. To address these phenomena, we propose a Natural Language to Verified Image generation approach (NL2VI) that converts a natural prompt into a visual prompt, which is more suitable for image generation. A T2I model then generates an image for the visual prompt, which is then verified with VQA algorithms. Experimentally, aligning natural prompts with image generation can improve the consistency of the generated images by up to 11% over the state of the art. Moreover, improvements can generalize to challenging domains like cooking and DIY tasks, where the correctness of the generated image is crucial to illustrate actions.

Authors:Shilv Cai, Xu Zou, Liqun Chen, Luxin Yan, Sheng Zhong

Abstract: Learning-based image compression methods have made great progress. Most of them are designed for generic natural images. In fact, low-light images frequently occur due to unavoidable environmental influences or technical limitations, such as insufficient lighting or limited exposure time. %When general-purpose image compression algorithms compress low-light images, useful detail information is lost, resulting in a dramatic decrease in image enhancement. Once low-light images are compressed by existing general image compression approaches, useful information(e.g., texture details) would be lost resulting in a dramatic performance decrease in low-light image enhancement. To simultaneously achieve a higher compression rate and better enhancement performance for low-light images, we propose a novel image compression framework with joint optimization of low-light image enhancement. We design an end-to-end trainable two-branch architecture with lower computational cost, which includes the main enhancement branch and the signal-to-noise ratio~(SNR) aware branch. Experimental results show that our proposed joint optimization framework achieves a significant improvement over existing ``Compress before Enhance" or ``Enhance before Compress" sequential solutions for low-light images. Source codes are included in the supplementary material.

Authors:Yuxuan Sun, Chenglu Zhu, Sunyi Zheng, Kai Zhang, Zhongyi Shui, Xiaoxuan Yu, Yizhi Zhao, Honglin Li, Yunlong Zhang, Ruojia Zhao, Xinheng Lyu, Lin Yang

Abstract: As advances in large language models (LLMs) and multimodal techniques continue to mature, the development of general-purpose multimodal large language models (MLLMs) has surged, with significant applications in natural image interpretation. However, the field of pathology has largely remained untapped in this regard, despite the growing need for accurate, timely, and personalized diagnostics. To bridge the gap in pathology MLLMs, we present the PathAsst in this study, which is a generative foundation AI assistant to revolutionize diagnostic and predictive analytics in pathology. To develop PathAsst, we collect over 142K high-quality pathology image-text pairs from a variety of reliable sources, including PubMed, comprehensive pathology textbooks, reputable pathology websites, and private data annotated by pathologists. Leveraging the advanced capabilities of ChatGPT/GPT-4, we generate over 180K instruction-following samples. Furthermore, we devise additional instruction-following data, specifically tailored for the invocation of the pathology-specific models, allowing the PathAsst to effectively interact with these models based on the input image and user intent, consequently enhancing the model's diagnostic capabilities. Subsequently, our PathAsst is trained based on Vicuna-13B language model in coordination with the CLIP vision encoder. The results of PathAsst show the potential of harnessing the AI-powered generative foundation model to improve pathology diagnosis and treatment processes. We are committed to open-sourcing our meticulously curated dataset, as well as a comprehensive toolkit designed to aid researchers in the extensive collection and preprocessing of their own datasets. Resources can be obtained at https://github.com/superjamessyx/Generative-Foundation-AI-Assistant-for-Pathology.

Authors:Yunfan Lu, Guoqiang Liang, Lin Wang

Abstract: Images captured by rolling shutter (RS) cameras under fast camera motion often contain obvious image distortions and blur, which can be modeled as a row-wise combination of a sequence of global shutter (GS) frames within the exposure time naturally, recovering high-frame-rate GS sharp frames from an RS blur image needs to simultaneously consider RS correction, deblur, and frame interpolation Taking this task is nontrivial, and to our knowledge, no feasible solutions exist by far. A naive way is to decompose the complete process into separate tasks and simply cascade existing methods; however, this results in cumulative errors and noticeable artifacts. Event cameras enjoy many advantages, e.g., high temporal resolution, making them potential for our problem. To this end, we make the first attempt to recover high-frame-rate sharp GS frames from an RS blur image and paired event data. Our key idea is to learn an implicit neural representation (INR) to directly map the position and time coordinates to RGB values to address the interlocking degradations in the image restoration process. Specifically, we introduce spatial-temporal implicit encoding (STE) to convert an RS blur image and events into a spatial-temporal representation (STR). To query a specific sharp frame (GS or RS), we embed the exposure time into STR and decode the embedded features to recover a sharp frame. Moreover, we propose an RS blur image-guided integral loss to better train the network. Our method is relatively lightweight as it contains only 0.379M parameters and demonstrates high efficiency as the STE is called only once for any number of interpolation frames. Extensive experiments show that our method significantly outperforms prior methods addressing only one or two of the tasks.

Authors:Błażej Leporowski, Arian Bakhtiarnia, Nicole Bonnici, Adrian Muscat, Luca Zanella, Yiming Wang, Alexandros Iosifidis

Abstract: We introduce the first audio-visual dataset for traffic anomaly detection taken from real-world scenes, called MAVAD, with a diverse range of weather and illumination conditions. In addition, we propose a novel method named AVACA that combines visual and audio features extracted from video sequences by means of cross-attention to detect anomalies. We demonstrate that the addition of audio improves the performance of AVACA by up to 5.2%. We also evaluate the impact of image anonymization, showing only a minor decrease in performance averaging at 1.7%.

Authors:Beomsu Kim, Gihyun Kwon, Kwanyoung Kim, Jong Chul Ye

Abstract: Diffusion models are a powerful class of generative models which simulate stochastic differential equations (SDEs) to generate data from noise. Although diffusion models have achieved remarkable progress in recent years, they have limitations in the unpaired image-to-image translation tasks due to the Gaussian prior assumption. Schr\"odinger Bridge (SB), which learns an SDE to translate between two arbitrary distributions, have risen as an attractive solution to this problem. However, none of SB models so far have been successful at unpaired translation between high-resolution images. In this work, we propose the Unpaired Neural Schr\"odinger Bridge (UNSB), which combines SB with adversarial training and regularization to learn a SB between unpaired data. We demonstrate that UNSB is scalable, and that it successfully solves various unpaired image-to-image translation tasks. Code: \url{https://github.com/cyclomon/UNSB}

Authors:Zouhayra Ayadi, Wadii Boulila, Imed Riadh Farah

Abstract: This paper proposes a method for automatically monitoring and analyzing the evolution of complex geographic objects. The objects are modeled as a spatiotemporal graph, which separates filiation relations, spatial relations, and spatiotemporal relations, and is analyzed by detecting frequent sub-graphs using constraint satisfaction problems (CSP). The process is divided into four steps: first, the identification of complex objects in each satellite image; second, the construction of a spatiotemporal graph to model the spatiotemporal changes of the complex objects; third, the creation of sub-graphs to be detected in the base spatiotemporal graph; and fourth, the analysis of the spatiotemporal graph by detecting the sub-graphs and solving a constraint network to determine relevant sub-graphs. The final step is further broken down into two sub-steps: (i) the modeling of the constraint network with defined variables and constraints, and (ii) the solving of the constraint network to find relevant sub-graphs in the spatiotemporal graph. Experiments were conducted using real-world satellite images representing several cities in Saudi Arabia, and the results demonstrate the effectiveness of the proposed approach.

Authors:Dongqing Wang, Tong Zhang, Alaa Abboud, Sabine Süsstrunk

Abstract: Neural Radiance Fields (NeRF) can generate highly realistic novel views. However, editing 3D scenes represented by NeRF across 360-degree views, particularly removing objects while preserving geometric and photometric consistency, remains a challenging problem due to NeRF's implicit scene representation. In this paper, we propose InpaintNeRF360, a unified framework that utilizes natural language instructions as guidance for inpainting NeRF-based 3D scenes.Our approach employs a promptable segmentation model by generating multi-modal prompts from the encoded text for multiview segmentation. We apply depth-space warping to enforce viewing consistency in the segmentations, and further refine the inpainted NeRF model using perceptual priors to ensure visual plausibility. InpaintNeRF360 is capable of simultaneously removing multiple objects or modifying object appearance based on text instructions while synthesizing 3D viewing-consistent and photo-realistic inpainting. Through extensive experiments on both unbounded and frontal-facing scenes trained through NeRF, we demonstrate the effectiveness of our approach and showcase its potential to enhance the editability of implicit radiance fields.

Authors:Jiesheng Yang, Andreas Wilde, Karsten Menzel, Md Zubair Sheikh, Boris Kuznetsov

Abstract: Construction progress monitoring (CPM) is essential for effective project management, ensuring on-time and on-budget delivery. Traditional CPM methods often rely on manual inspection and reporting, which are time-consuming and prone to errors. This paper proposes a novel approach for automated CPM using state-of-the-art object detection algorithms. The proposed method leverages e.g. YOLOv8's real-time capabilities and high accuracy to identify and track construction elements within site images and videos. A dataset was created, consisting of various building elements and annotated with relevant objects for training and validation. The performance of the proposed approach was evaluated using standard metrics, such as precision, recall, and F1-score, demonstrating significant improvement over existing methods. The integration of Computer Vision into CPM provides stakeholders with reliable, efficient, and cost-effective means to monitor project progress, facilitating timely decision-making and ultimately contributing to the successful completion of construction projects.

Authors:Lingtao Wang, Jianrui Ding, Fenghe Tang, Chunping Ning

Abstract: Accurate detection of thyroid lesions is a critical aspect of computer-aided diagnosis. However, most existing detection methods perform only one feature extraction process and then fuse multi-scale features, which can be affected by noise and blurred features in ultrasound images. In this study, we propose a novel detection network based on a feature feedback mechanism inspired by clinical diagnosis. The mechanism involves first roughly observing the overall picture and then focusing on the details of interest. It comprises two parts: a feedback feature selection module and a feature feedback pyramid. The feedback feature selection module efficiently selects the features extracted in the first phase in both space and channel dimensions to generate high semantic prior knowledge, which is similar to coarse observation. The feature feedback pyramid then uses this high semantic prior knowledge to enhance feature extraction in the second phase and adaptively fuses the two features, similar to fine observation. Additionally, since radiologists often focus on the shape and size of lesions for diagnosis, we propose an adaptive detection head strategy to aggregate multi-scale features. Our proposed method achieves an AP of 70.3% and AP50 of 99.0% on the thyroid ultrasound dataset and meets the real-time requirement. The code is available at https://github.com/HIT-wanglingtao/Thinking-Twice.

Authors:Jinjin Gu, Xianzheng Ma, Xiangtao Kong, Yu Qiao, Chao Dong

Abstract: Deep deraining networks, while successful in laboratory benchmarks, consistently encounter substantial generalization issues when deployed in real-world applications. A prevailing perspective in deep learning encourages the use of highly complex training data, with the expectation that a richer image content knowledge will facilitate overcoming the generalization problem. However, through comprehensive and systematic experimentation, we discovered that this strategy does not enhance the generalization capability of these networks. On the contrary, it exacerbates the tendency of networks to overfit to specific degradations. Our experiments reveal that better generalization in a deraining network can be achieved by simplifying the complexity of the training data. This is due to the networks are slacking off during training, that is, learning the least complex elements in the image content and degradation to minimize training loss. When the complexity of the background image is less than that of the rain streaks, the network will prioritize the reconstruction of the background, thereby avoiding overfitting to the rain patterns and resulting in improved generalization performance. Our research not only offers a valuable perspective and methodology for better understanding the generalization problem in low-level vision tasks, but also displays promising practical potential.

Authors:Jana Kierdorf, Ribana Roscher

Abstract: Cauliflower is a hand-harvested crop that must fulfill high-quality standards in sales making the timing of harvest important. However, accurately determining harvest-readiness can be challenging due to the cauliflower head being covered by its canopy. While deep learning enables automated harvest-readiness estimation, errors can occur due to field-variability and limited training data. In this paper, we analyze the reliability of a harvest-readiness classifier with interpretable machine learning. By identifying clusters of saliency maps, we derive reliability scores for each classification result using knowledge about the domain and the image properties. For unseen data, the reliability can be used to (i) inform farmers to improve their decision-making and (ii) increase the model prediction accuracy. Using RGB images of single cauliflower plants at different developmental stages from the GrowliFlower dataset, we investigate various saliency mapping approaches and find that they result in different quality of reliability scores. With the most suitable interpretation tool, we adjust the classification result and achieve a 15.72% improvement of the overall accuracy to 88.14% and a 15.44% improvement of the average class accuracy to 88.52% for the GrowliFlower dataset.

Authors:Kiran Kokilepersaud, Stephanie Trejo Corona, Mohit Prabhushankar, Ghassan AlRegib, Charles Wykoff

Abstract: This paper presents a novel positive and negative set selection strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. In the medical field, there exists a variety of labels for data that serve different purposes at different stages of a diagnostic and treatment process. Clinical labels and biomarker labels are two examples. In general, clinical labels are easier to obtain in larger quantities because they are regularly collected during routine clinical care, while biomarker labels require expert analysis and interpretation to obtain. Within the field of ophthalmology, previous work has shown that clinical values exhibit correlations with biomarker structures that manifest within optical coherence tomography (OCT) scans. We exploit this relationship by using the clinical data as pseudo-labels for our data without biomarker labels in order to choose positive and negative instances for training a backbone network with a supervised contrastive loss. In this way, a backbone network learns a representation space that aligns with the clinical data distribution available. Afterwards, we fine-tune the network trained in this manner with the smaller amount of biomarker labeled data with a cross-entropy loss in order to classify these key indicators of disease directly from OCT scans. We also expand on this concept by proposing a method that uses a linear combination of clinical contrastive losses. We benchmark our methods against state of the art self-supervised methods in a novel setting with biomarkers of varying granularity. We show performance improvements by as much as 5\% in total biomarker detection AUROC.

Authors:Xinhang Liu, Shiu-hong Kao, Jiaben Chen, Yu-Wing Tai, Chi-Keung Tang

Abstract: This paper introduces Deceptive-NeRF, a new method for enhancing the quality of reconstructed NeRF models using synthetically generated pseudo-observations, capable of handling sparse input and removing floater artifacts. Our proposed method involves three key steps: 1) reconstruct a coarse NeRF model from sparse inputs; 2) generate pseudo-observations based on the coarse model; 3) refine the NeRF model using pseudo-observations to produce a high-quality reconstruction. To generate photo-realistic pseudo-observations that faithfully preserve the identity of the reconstructed scene while remaining consistent with the sparse inputs, we develop a rectification latent diffusion model that generates images conditional on a coarse RGB image and depth map, which are derived from the coarse NeRF and latent text embedding from input images. Extensive experiments show that our method is effective and can generate perceptually high-quality NeRF even with very sparse inputs.

Authors:Sungnyun Kim, Junsoo Lee, Kibeom Hong, Daesik Kim, Namhyuk Ahn

Abstract: The recent progress in diffusion-based text-to-image generation models has significantly expanded generative capabilities via conditioning the text descriptions. However, since relying solely on text prompts is still restrictive for fine-grained customization, we aim to extend the boundaries of conditional generation to incorporate diverse types of modalities, e.g., sketch, box, and style embedding, simultaneously. We thus design a multimodal text-to-image diffusion model, coined as DiffBlender, that achieves the aforementioned goal in a single model by training only a few small hypernetworks. DiffBlender facilitates a convenient scaling of input modalities, without altering the parameters of an existing large-scale generative model to retain its well-established knowledge. Furthermore, our study sets new standards for multimodal generation by conducting quantitative and qualitative comparisons with existing approaches. By diversifying the channels of conditioning modalities, DiffBlender faithfully reflects the provided information or, in its absence, creates imaginative generation.

Authors:Nathan Vance, Jeremy Speth, Benjamin Sporrer, Patrick Flynn

Abstract: Remote Photoplethysmography (rPPG), or the remote monitoring of a subject's heart rate using a camera, has seen a shift from handcrafted techniques to deep learning models. While current solutions offer substantial performance gains, we show that these models tend to learn a bias to pulse wave features inherent to the training dataset. We develop augmentations to mitigate this learned bias by expanding both the range and variability of heart rates that the model sees while training, resulting in improved model convergence when training and cross-dataset generalization at test time. Through a 3-way cross dataset analysis we demonstrate a reduction in mean absolute error from over 13 beats per minute to below 3 beats per minute. We compare our method with other recent rPPG systems, finding similar performance under a variety of evaluation parameters.

Authors:Wei Zhou, Qian Wang, Weiwei Jin, Xinzhe Shi, Dekui Wang, Xingxing Hao, Yongxiang Yu

Abstract: Recently, graph-based and Transformer-based deep learning networks have demonstrated excellent performances on various point cloud tasks. Most of the existing graph methods are based on static graph, which take a fixed input to establish graph relations. Moreover, many graph methods apply maximization and averaging to aggregate neighboring features, so that only a single neighboring point affects the feature of centroid or different neighboring points have the same influence on the centroid's feature, which ignoring the correlation and difference between points. Most Transformer-based methods extract point cloud features based on global attention and lack the feature learning on local neighbors. To solve the problems of these two types of models, we propose a new feature extraction block named Graph Transformer and construct a 3D point point cloud learning network called GTNet to learn features of point clouds on local and global patterns. Graph Transformer integrates the advantages of graph-based and Transformer-based methods, and consists of Local Transformer and Global Transformer modules. Local Transformer uses a dynamic graph to calculate all neighboring point weights by intra-domain cross-attention with dynamically updated graph relations, so that every neighboring point could affect the features of centroid with different weights; Global Transformer enlarges the receptive field of Local Transformer by a global self-attention. In addition, to avoid the disappearance of the gradient caused by the increasing depth of network, we conduct residual connection for centroid features in GTNet; we also adopt the features of centroid and neighbors to generate the local geometric descriptors in Local Transformer to strengthen the local information learning capability of the model. Finally, we use GTNet for shape classification, part segmentation and semantic segmentation tasks in this paper.

Authors:Zheng Chang, Shuchen Weng, Peixuan Zhang, Yu Li, Si Li, Boxin Shi

Abstract: Language-based colorization produces plausible and visually pleasing colors under the guidance of user-friendly natural language descriptions. Previous methods implicitly assume that users provide comprehensive color descriptions for most of the objects in the image, which leads to suboptimal performance. In this paper, we propose a unified model to perform language-based colorization with any-level descriptions. We leverage the pretrained cross-modality generative model for its robust language understanding and rich color priors to handle the inherent ambiguity of any-level descriptions. We further design modules to align with input conditions to preserve local spatial structures and prevent the ghosting effect. With the proposed novel sampling strategy, our model achieves instance-aware colorization in diverse and complex scenarios. Extensive experimental results demonstrate our advantages of effectively handling any-level descriptions and outperforming both language-based and automatic colorization methods. The code and pretrained models are available at: https://github.com/changzheng123/L-CAD.

Authors:Yao Rong, Xiangyu Wei, Tianwei Lin, Yueyu Wang, Enkelejda Kasneci

Abstract: Augmenting LiDAR input with multiple previous frames provides richer semantic information and thus boosts performance in 3D object detection, However, crowded point clouds in multi-frames can hurt the precise position information due to the motion blur and inaccurate point projection. In this work, we propose a novel feature fusion strategy, DynStaF (Dynamic-Static Fusion), which enhances the rich semantic information provided by the multi-frame (dynamic branch) with the accurate location information from the current single-frame (static branch). To effectively extract and aggregate complimentary features, DynStaF contains two modules, Neighborhood Cross Attention (NCA) and Dynamic-Static Interaction (DSI), operating through a dual pathway architecture. NCA takes the features in the static branch as queries and the features in the dynamic branch as keys (values). When computing the attention, we address the sparsity of point clouds and take only neighborhood positions into consideration. NCA fuses two features at different feature map scales, followed by DSI providing the comprehensive interaction. To analyze our proposed strategy DynStaF, we conduct extensive experiments on the nuScenes dataset. On the test set, DynStaF increases the performance of PointPillars in NDS by a large margin from 57.7% to 61.6%. When combined with CenterPoint, our framework achieves 61.0% mAP and 67.7% NDS, leading to state-of-the-art performance without bells and whistles.

Authors:Anja Delić, Matej Grcić, Siniša Šegvić

Abstract: Most approaches to dense anomaly detection rely on generative modeling or on discriminative methods that train with negative data. We consider a recent hybrid method that optimizes the same shared representation according to cross-entropy of the discriminative predictions, and negative log likelihood of the predicted energy-based density. We extend that work with a jointly trained generative flow that samples synthetic negatives at the border of the inlier distribution. The proposed extension provides potential to learn the hybrid method without real negative data. Our experiments analyze the impact of training with synthetic negative data and validate contribution of the energy-based density during training and evaluation.

Authors:Huanran Chen, Yinpeng Dong, Zhengyi Wang, Xiao Yang, Chengqi Duan, Hang Su, Jun Zhu

Abstract: Recently, diffusion models have been successfully applied to improving adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, the diffusion-based purification can be evaded by stronger adaptive attacks while adversarial training does not perform well under unseen threats, exhibiting inevitable limitations of these methods. To better harness the expressive power of diffusion models, in this paper we propose Robust Diffusion Classifier (RDC), a generative classifier that is constructed from a pre-trained diffusion model to be adversarially robust. Our method first maximizes the data likelihood of a given input and then predicts the class probabilities of the optimized input using the conditional likelihood of the diffusion model through Bayes' theorem. Since our method does not require training on particular adversarial attacks, we demonstrate that it is more generalizable to defend against multiple unseen threats. In particular, RDC achieves $73.24\%$ robust accuracy against $\ell_\infty$ norm-bounded perturbations with $\epsilon_\infty=8/255$ on CIFAR-10, surpassing the previous state-of-the-art adversarial training models by $+2.34\%$. The findings highlight the potential of generative classifiers by employing diffusion models for adversarial robustness compared with the commonly studied discriminative classifiers.

Authors:Cheng-Ze Lu, Xiaojie Jin, Qibin Hou, Jun Hao Liew, Ming-Ming Cheng, Jiashi Feng

Abstract: Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the scaling capability of masked image modeling (MIM) methods (e.g., MAE) for visual recognition. Unlike most previous works that depend on the widely-used ImageNet dataset, which is manually curated and object-centric, we take a step further and propose to investigate this problem in a more practical setting. Specifically, we utilize the web-collected Coyo-700M dataset. We randomly sample varying numbers of training images from the Coyo dataset and construct a series of sub-datasets, containing 0.5M, 1M, 5M, 10M, and 100M images, for pre-training. Our goal is to investigate how the performance changes on downstream tasks when scaling with different sizes of data and models. The study reveals that: 1) MIM can be viewed as an effective method to improve the model capacity when the scale of the training data is relatively small; 2) Strong reconstruction targets can endow the models with increased capacities on downstream tasks; 3) MIM pre-training is data-agnostic under most scenarios, which means that the strategy of sampling pre-training data is non-critical. We hope these observations could provide valuable insights for future research on MIM.

Authors:Tong Xu, Micol Spitale, Hao Tang, Lu Liu, Hatice Gunes, Siyang Song

Abstract: Generating facial reactions in a human-human dyadic interaction is complex and highly dependent on the context since more than one facial reactions can be appropriate for the speaker's behaviour. This has challenged existing machine learning (ML) methods, whose training strategies enforce models to reproduce a specific (not multiple) facial reaction from each input speaker behaviour. This paper proposes the first multiple appropriate facial reaction generation framework that re-formulates the one-to-many mapping facial reaction generation problem as a one-to-one mapping problem. This means that we approach this problem by considering the generation of a distribution of the listener's appropriate facial reactions instead of multiple different appropriate facial reactions, i.e., 'many' appropriate facial reaction labels are summarised as 'one' distribution label during training. Our model consists of a perceptual processor, a cognitive processor, and a motor processor. The motor processor is implemented with a novel Reversible Multi-dimensional Edge Graph Neural Network (REGNN). This allows us to obtain a distribution of appropriate real facial reactions during the training process, enabling the cognitive processor to be trained to predict the appropriate facial reaction distribution. At the inference stage, the REGNN decodes an appropriate facial reaction by using this distribution as input. Experimental results demonstrate that our approach outperforms existing models in generating more appropriate, realistic, and synchronized facial reactions. The improved performance is largely attributed to the proposed appropriate facial reaction distribution learning strategy and the use of a REGNN. The code is available at https://github.com/TongXu-05/REGNN-Multiple-Appropriate-Facial-Reaction-Generation.

Authors:Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang

Abstract: Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image matting. We hypothesize that image matting could also be boosted by ViTs and present a new efficient and robust ViT-based matting system, named ViTMatte. Our method utilizes (i) a hybrid attention mechanism combined with a convolution neck to help ViTs achieve an excellent performance-computation trade-off in matting tasks. (ii) Additionally, we introduce the detail capture module, which just consists of simple lightweight convolutions to complement the detailed information required by matting. To the best of our knowledge, ViTMatte is the first work to unleash the potential of ViT on image matting with concise adaptation. It inherits many superior properties from ViT to matting, including various pretraining strategies, concise architecture design, and flexible inference strategies. We evaluate ViTMatte on Composition-1k and Distinctions-646, the most commonly used benchmark for image matting, our method achieves state-of-the-art performance and outperforms prior matting works by a large margin.

Authors:Enrico Picco, Piotr Antonik, Serge Massar

Abstract: The recognition of human actions in videos is one of the most active research fields in computer vision. The canonical approach consists in a more or less complex preprocessing stages of the raw video data, followed by a relatively simple classification algorithm. Here we address recognition of human actions using the reservoir computing algorithm, which allows us to focus on the classifier stage. We introduce a new training method for the reservoir computer, based on "Timesteps Of Interest", which combines in a simple way short and long time scales. We study the performance of this algorithm using both numerical simulations and a photonic implementation based on a single non-linear node and a delay line on the well known KTH dataset. We solve the task with high accuracy and speed, to the point of allowing for processing multiple video streams in real time. The present work is thus an important step towards developing efficient dedicated hardware for video processing.

Authors:Marco Bellagente, Manuel Brack, Hannah Teufel, Felix Friedrich, Björn Deiseroth, Constantin Eichenberg, Andrew Dai, Robert Baldock, Souradeep Nanda, Koen Oostermeijer, Andres Felipe Cruz-Salinas, Patrick Schramowski, Kristian Kersting, Samuel Weinbach

Abstract: The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations of text prompts. However, expressing complex or nuanced ideas in text alone can be difficult. To ease image generation, we propose MultiFusion that allows one to express complex and nuanced concepts with arbitrarily interleaved inputs of multiple modalities and languages. MutliFusion leverages pre-trained models and aligns them for integration into a cohesive system, thereby avoiding the need for extensive training from scratch. Our experimental results demonstrate the efficient transfer of capabilities from individual modules to the downstream model. Specifically, the fusion of all independent components allows the image generation module to utilize multilingual, interleaved multimodal inputs despite being trained solely on monomodal data in a single language.

Authors:Chang Liu, Henghui Ding, Yulun Zhang, Xudong Jiang

Abstract: We address the problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression. Many recent works utilize Transformer to extract features for the target object by aggregating the attended visual regions. However, the generic attention mechanism in Transformer only uses the language input for attention weight calculation, which does not explicitly fuse language features in its output. Thus, its output feature is dominated by vision information, which limits the model to comprehensively understand the multi-modal information, and brings uncertainty for the subsequent mask decoder to extract the output mask. To address this issue, we propose Multi-Modal Mutual Attention ($\mathrm{M^3Att}$) and Multi-Modal Mutual Decoder ($\mathrm{M^3Dec}$) that better fuse information from the two input modalities. Based on {$\mathrm{M^3Dec}$}, we further propose Iterative Multi-modal Interaction ($\mathrm{IMI}$) to allow continuous and in-depth interactions between language and vision features. Furthermore, we introduce Language Feature Reconstruction ($\mathrm{LFR}$) to prevent the language information from being lost or distorted in the extracted feature. Extensive experiments show that our proposed approach significantly improves the baseline and outperforms state-of-the-art referring image segmentation methods on RefCOCO series datasets consistently.

Authors:Yongchao Zhou, Hshmat Sahak, Jimmy Ba

Abstract: Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the pre-trained generative model, Stable Diffusion, to generate diverse, high-quality training data for image classification. Our approach captures the original data distribution and ensures data coverage by inverting images to the latent space of Stable Diffusion, and generates diverse novel training images by conditioning the generative model on noisy versions of these vectors. We identify three key components that allow our generated images to successfully supplant the original dataset, leading to a 2-3x enhancement in sample complexity and a 6.5x decrease in sampling time. Moreover, our approach consistently outperforms generic prompt-based steering methods and KNN retrieval baseline across a wide range of datasets. Additionally, we demonstrate the compatibility of our approach with widely-used data augmentation techniques, as well as the reliability of the generated data in supporting various neural architectures and enhancing few-shot learning.

Authors:Jaemin Cho, Abhay Zala, Mohit Bansal

Abstract: As large language models have demonstrated impressive performance in many domains, recent works have adopted language models (LMs) as controllers of visual modules for vision-and-language tasks. While existing work focuses on equipping LMs with visual understanding, we propose two novel interpretable/explainable visual programming frameworks for text-to-image (T2I) generation and evaluation. First, we introduce VPGen, an interpretable step-by-step T2I generation framework that decomposes T2I generation into three steps: object/count generation, layout generation, and image generation. We employ an LM to handle the first two steps (object/count generation and layout generation), by finetuning it on text-layout pairs. Our step-by-step T2I generation framework provides stronger spatial control than end-to-end models, the dominant approach for this task. Furthermore, we leverage the world knowledge of pretrained LMs, overcoming the limitation of previous layout-guided T2I works that can only handle predefined object classes. We demonstrate that our VPGen has improved control in counts/spatial relations/scales of objects than state-of-the-art T2I generation models. Second, we introduce VPEval, an interpretable and explainable evaluation framework for T2I generation based on visual programming. Unlike previous T2I evaluations with a single scoring model that is accurate in some skills but unreliable in others, VPEval produces evaluation programs that invoke a set of visual modules that are experts in different skills, and also provides visual+textual explanations of the evaluation results. Our analysis shows VPEval provides a more human-correlated evaluation for skill-specific and open-ended prompts than widely used single model-based evaluation. We hope our work encourages future progress on interpretable/explainable generation and evaluation for T2I models. Website: https://vp-t2i.github.io

Authors:Junyi Zhang, Charles Herrmann, Junhwa Hur, Luisa Polania Cabrera, Varun Jampani, Deqing Sun, Ming-Hsuan Yang

Abstract: Text-to-image diffusion models have made significant advances in generating and editing high-quality images. As a result, numerous approaches have explored the ability of diffusion model features to understand and process single images for downstream tasks, e.g., classification, semantic segmentation, and stylization. However, significantly less is known about what these features reveal across multiple, different images and objects. In this work, we exploit Stable Diffusion (SD) features for semantic and dense correspondence and discover that with simple post-processing, SD features can perform quantitatively similar to SOTA representations. Interestingly, the qualitative analysis reveals that SD features have very different properties compared to existing representation learning features, such as the recently released DINOv2: while DINOv2 provides sparse but accurate matches, SD features provide high-quality spatial information but sometimes inaccurate semantic matches. We demonstrate that a simple fusion of these two features works surprisingly well, and a zero-shot evaluation using nearest neighbors on these fused features provides a significant performance gain over state-of-the-art methods on benchmark datasets, e.g., SPair-71k, PF-Pascal, and TSS. We also show that these correspondences can enable interesting applications such as instance swapping in two images.

Authors:Feifei Shao, Yawei Luo, Lei Chen, Ping Liu, Yi Yang, Jun Xiao

Abstract: In this paper, we focus on an under-explored issue of biased activation in prior weakly-supervised object localization methods based on Class Activation Mapping (CAM). We analyze the cause of this problem from a causal view and attribute it to the co-occurring background confounders. Following this insight, we propose a novel Counterfactual Co-occurring Learning (CCL) paradigm to synthesize the counterfactual representations via coupling constant foreground and unrealized backgrounds in order to cut off their co-occurring relationship. Specifically, we design a new network structure called Counterfactual-CAM, which embeds the counterfactual representation perturbation mechanism into the vanilla CAM-based model. This mechanism is responsible for decoupling foreground as well as background and synthesizing the counterfactual representations. By training the detection model with these synthesized representations, we compel the model to focus on the constant foreground content while minimizing the influence of distracting co-occurring background. To our best knowledge, it is the first attempt in this direction. Extensive experiments on several benchmarks demonstrate that Counterfactual-CAM successfully mitigates the biased activation problem, achieving improved object localization accuracy.

Authors:Mahla Abdolahnejad, Justin Lee, Hannah Chan, Alex Morzycki, Olivier Ethier, Anthea Mo, Peter X. Liu, Joshua N. Wong, Colin Hong, Rakesh Joshi

Abstract: Burn injuries can result from mechanisms such as thermal, chemical, and electrical insults. A prompt and accurate assessment of burns is essential for deciding definitive clinical treatments. Currently, the primary approach for burn assessments, via visual and tactile observations, is approximately 60%-80% accurate. The gold standard is biopsy and a close second would be non-invasive methods like Laser Doppler Imaging (LDI) assessments, which have up to 97% accuracy in predicting burn severity and the required healing time. In this paper, we introduce a machine learning pipeline for assessing burn severities and segmenting the regions of skin that are affected by burn. Segmenting 2D colour images of burns allows for the injured versus non-injured skin to be delineated, clearly marking the extent and boundaries of the localized burn/region-of-interest, even during remote monitoring of a burn patient. We trained a convolutional neural network (CNN) to classify four severities of burns. We built a saliency mapping method, Boundary Attention Mapping (BAM), that utilises this trained CNN for the purpose of accurately localizing and segmenting the burn regions from skin burn images. We demonstrated the effectiveness of our proposed pipeline through extensive experiments and evaluations using two datasets; 1) A larger skin burn image dataset consisting of 1684 skin burn images of four burn severities, 2) An LDI dataset that consists of a total of 184 skin burn images with their associated LDI scans. The CNN trained using the first dataset achieved an average F1-Score of 78% and micro/macro- average ROC of 85% in classifying the four burn severities. Moreover, a comparison between the BAM results and LDI results for measuring injury boundary showed that the segmentations generated by our method achieved 91.60% accuracy, 78.17% sensitivity, and 93.37% specificity.

Authors:Yunxiang Li, Meixu Chen, Wenxuan Yang, Kai Wang, Jun Ma, Alan C. Bovik, You Zhang

Abstract: Image translation has wide applications, such as style transfer and modality conversion, usually aiming to generate images having both high degrees of realism and faithfulness. These problems remain difficult, especially when it is important to preserve semantic structures. Traditional image-level similarity metrics are of limited use, since the semantics of an image are high-level, and not strongly governed by pixel-wise faithfulness to an original image. Towards filling this gap, we introduce SAMScore, a generic semantic structural similarity metric for evaluating the faithfulness of image translation models. SAMScore is based on the recent high-performance Segment Anything Model (SAM), which can perform semantic similarity comparisons with standout accuracy. We applied SAMScore on 19 image translation tasks, and found that it is able to outperform all other competitive metrics on all of the tasks. We envision that SAMScore will prove to be a valuable tool that will help to drive the vibrant field of image translation, by allowing for more precise evaluations of new and evolving translation models. The code is available at https://github.com/Kent0n-Li/SAMScore.

Authors:A. Emin Orhan, Brenden M. Lake

Abstract: Young children develop sophisticated internal models of the world based on their egocentric visual experience. How much of this is driven by innate constraints and how much is driven by their experience? To investigate these questions, we train state-of-the-art neural networks on a realistic proxy of a child's visual experience without any explicit supervision or domain-specific inductive biases. Specifically, we train both embedding models and generative models on 200 hours of headcam video from a single child collected over two years. We train a total of 72 different models, exploring a range of model architectures and self-supervised learning algorithms, and comprehensively evaluate their performance in downstream tasks. The best embedding models perform at 70% of a highly performant ImageNet-trained model on average. They also learn broad semantic categories without any labeled examples and learn to localize semantic categories in an image without any location supervision. However, these models are less object-centric and more background-sensitive than comparable ImageNet-trained models. Generative models trained with the same data successfully extrapolate simple properties of partially masked objects, such as their texture, color, orientation, and rough outline, but struggle with finer object details. We replicate our experiments with two other children and find very similar results. Broadly useful high-level visual representations are thus robustly learnable from a representative sample of a child's visual experience without strong inductive biases.