Computer Vision and Pattern Recognition (cs.CV)

Abstract: Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While techniques for feature tracking based on deep learning are a promising alternative to current human-in-the-loop processes, designing deep architectures that can operate onboard spacecraft is challenging due to onboard computational and memory constraints. This paper introduces a novel deep local feature description architecture that leverages binary convolutional neural network layers to significantly reduce computational and memory requirements. We train and test our models on real images of small bodies from legacy and ongoing missions and demonstrate increased performance relative to traditional handcrafted methods. Moreover, we implement our models onboard a surrogate for the next-generation spacecraft processor and demonstrate feasible runtimes for online feature tracking.

Abstract: Recent state-of-the-art methods for HOI detection typically build on transformer architectures with two decoder branches, one for human-object pair detection and the other for interaction classification. Such disentangled transformers, however, may suffer from insufficient context exchange between the branches and lead to a lack of context information for relational reasoning, which is critical in discovering HOI instances. In this work, we propose the multiplex relation network (MUREN) that performs rich context exchange between three decoder branches using unary, pairwise, and ternary relations of human, object, and interaction tokens. The proposed method learns comprehensive relational contexts for discovering HOI instances, achieving state-of-the-art performance on two standard benchmarks for HOI detection, HICO-DET and V-COCO.

Abstract: Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training. To alleviate the catastrophic forgetting issue in CSS, a memory buffer that stores a small number of samples from the previous classes is constructed for replay. However, existing methods select the memory samples either randomly or based on a single-factor-driven handcrafted strategy, which has no guarantee to be optimal. In this work, we propose a novel memory sample selection mechanism that selects informative samples for effective replay in a fully automatic way by considering comprehensive factors including sample diversity and class performance. Our mechanism regards the selection operation as a decision-making process and learns an optimal selection policy that directly maximizes the validation performance on a reward set. To facilitate the selection decision, we design a novel state representation and a dual-stage action space. Our extensive experiments on Pascal-VOC 2012 and ADE 20K datasets demonstrate the effectiveness of our approach with state-of-the-art (SOTA) performance achieved, outperforming the second-place one by 12.54% for the 6stage setting on Pascal-VOC 2012.

Abstract: Purpose: A fundamental problem in designing safe machine learning systems is identifying when samples presented to a deployed model differ from those observed at training time. Detecting so-called out-of-distribution (OoD) samples is crucial in safety-critical applications such as robotically-guided retinal microsurgery, where distances between the instrument and the retina are derived from sequences of 1D images that are acquired by an instrument-integrated optical coherence tomography (iiOCT) probe. Methods: This work investigates the feasibility of using an OoD detector to identify when images from the iiOCT probe are inappropriate for subsequent machine learning-based distance estimation. We show how a simple OoD detector based on the Mahalanobis distance can successfully reject corrupted samples coming from real-world ex-vivo porcine eyes. Results: Our results demonstrate that the proposed approach can successfully detect OoD samples and help maintain the performance of the downstream task within reasonable levels. MahaAD outperformed a supervised approach trained on the same kind of corruptions and achieved the best performance in detecting OoD cases from a collection of iiOCT samples with real-world corruptions. Conclusion: The results indicate that detecting corrupted iiOCT data through OoD detection is feasible and does not need prior knowledge of possible corruptions. Consequently, MahaAD could aid in ensuring patient safety during robotically-guided microsurgery by preventing deployed prediction models from estimating distances that put the patient at risk.

Abstract: Disease diagnosis from medical images via supervised learning is usually dependent on tedious, error-prone, and costly image labeling by medical experts. Alternatively, semi-supervised learning and self-supervised learning offer effectiveness through the acquisition of valuable insights from readily available unlabeled images. We present Semi-Supervised Relational Contrastive Learning (SRCL), a novel semi-supervised learning model that leverages self-supervised contrastive loss and sample relation consistency for the more meaningful and effective exploitation of unlabeled data. Our experimentation with the SRCL model explores both pre-train/fine-tune and joint learning of the pretext (contrastive learning) and downstream (diagnostic classification) tasks. We validate against the ISIC 2018 Challenge benchmark skin lesion classification dataset and demonstrate the effectiveness of our semi-supervised method on varying amounts of labeled data.

Abstract: In this work, we investigate the potential threat of adversarial examples to the security of face recognition systems. Although previous research has explored the adversarial risk to individual components of FRSs, our study presents an initial exploration of an adversary simultaneously fooling multiple components: the face detector and feature extractor in an FRS pipeline. We propose three multi-objective attacks on FRSs and demonstrate their effectiveness through a preliminary experimental analysis on a target system. Our attacks achieved up to 100% Attack Success Rates against both the face detector and feature extractor and were able to manipulate the face detection probability by up to 50% depending on the adversarial objective. This research identifies and examines novel attack vectors against FRSs and suggests possible ways to augment the robustness by leveraging the attack vector's knowledge during training of an FRS's components.

Abstract: Fashion vision-language pre-training models have shown efficacy for a wide range of downstream tasks. However, general vision-language pre-training models pay less attention to fine-grained domain features, while these features are important in distinguishing the specific domain tasks from general tasks. We propose a method for fine-grained fashion vision-language pre-training based on fashion Symbols and Attributes Prompt (FashionSAP) to model fine-grained multi-modalities fashion attributes and characteristics. Firstly, we propose the fashion symbols, a novel abstract fashion concept layer, to represent different fashion items and to generalize various kinds of fine-grained fashion features, making modelling fine-grained attributes more effective. Secondly, the attributes prompt method is proposed to make the model learn specific attributes of fashion items explicitly. We design proper prompt templates according to the format of fashion data. Comprehensive experiments are conducted on two public fashion benchmarks, i.e., FashionGen and FashionIQ, and FashionSAP gets SOTA performances for four popular fashion tasks. The ablation study also shows the proposed abstract fashion symbols, and the attribute prompt method enables the model to acquire fine-grained semantics in the fashion domain effectively. The obvious performance gains from FashionSAP provide a new baseline for future fashion task research.

Abstract: Diffusion models are a leading method for image generation and have been successfully applied in magnetic resonance imaging (MRI) reconstruction. Current diffusion-based reconstruction methods rely on coil sensitivity maps (CSM) to reconstruct multi-coil data. However, it is difficult to accurately estimate CSMs in practice use, resulting in degradation of the reconstruction quality. To address this issue, we propose a self-consistency-driven diffusion model inspired by the iterative self-consistent parallel imaging (SPIRiT), namely SPIRiT-Diffusion. Specifically, the iterative solver of the self-consistent term in SPIRiT is utilized to design a novel stochastic differential equation (SDE) for diffusion process. Then $\textit{k}$-space data can be interpolated directly during the reverse diffusion process, instead of using CSM to separate and combine individual coil images. This method indicates that the optimization model can be used to design SDE in diffusion models, driving the diffusion process strongly conforming with the physics involved in the optimization model, dubbed model-driven diffusion. The proposed SPIRiT-Diffusion method was evaluated on a 3D joint Intracranial and Carotid Vessel Wall imaging dataset. The results demonstrate that it outperforms the CSM-based reconstruction methods, and achieves high reconstruction quality at a high acceleration rate of 10.

Abstract: Hospital emergency departments frequently receive lots of bone fracture cases, with pediatric wrist trauma fracture accounting for the majority of them. Before pediatric surgeons perform surgery, they need to ask patients how the fracture occurred and analyze the fracture situation by interpreting X-ray images. The interpretation of X-ray images often requires a combination of techniques from radiologists and surgeons, which requires time-consuming specialized training. With the rise of deep learning in the field of computer vision, network models applying for fracture detection has become an important research topic. In this paper, YOLOv8 algorithm is used to train models on the GRAZPEDWRI-DX dataset, which includes X-ray images from 6,091 pediatric patients with wrist trauma. The experimental results show that YOLOv8 algorithm models have different advantages for different model sizes, with YOLOv8l model achieving the highest mean average precision (mAP 50) of 63.6\%, and YOLOv8n model achieving the inference time of 67.4ms per X-ray image on one single CPU with low computing power. In this way, we create "Fracture Detection Using YOLOv8 App" to assist surgeons in interpreting X-ray images without the help of radiologists. Our implementation code is released at https://github.com/RuiyangJu/Bone_Fracture_Detection_YOLOv8.

Abstract: Accurate urban maps provide essential information to support sustainable urban development. Recent urban mapping methods use multi-modal deep neural networks to fuse Synthetic Aperture Radar (SAR) and optical data. However, multi-modal networks may rely on just one modality due to the greedy nature of learning. In turn, the imbalanced utilization of modalities can negatively affect the generalization ability of a network. In this paper, we investigate the utilization of SAR and optical data for urban mapping. To that end, a dual-branch network architecture using intermediate fusion modules to share information between the uni-modal branches is utilized. A cut-off mechanism in the fusion modules enables the stopping of information flow between the branches, which is used to estimate the network's dependence on SAR and optical data. While our experiments on the SEN12 Global Urban Mapping dataset show that good performance can be achieved with conventional SAR-optical data fusion (F1 score = 0.682 $\pm$ 0.014), we also observed a clear under-utilization of optical data. Therefore, future work is required to investigate whether a more balanced utilization of SAR and optical data can lead to performance improvements.

Abstract: Though research has shown the complementarity of camera- and inertial-based data, datasets which offer both modalities remain scarce. In this paper we introduce WEAR, a multimodal benchmark dataset for both vision- and wearable-based Human Activity Recognition (HAR). The dataset comprises data from 18 participants performing a total of 18 different workout activities with untrimmed inertial (acceleration) and camera (egocentric video) data recorded at 10 different outside locations. WEAR features a diverse set of activities which are low in inter-class similarity and, unlike previous egocentric datasets, not defined by human-object-interactions nor originate from inherently distinct activity categories. Provided benchmark results reveal that single-modality architectures have different strengths and weaknesses in their prediction performance. Further, in light of the recent success of transformer-based video action detection models, we demonstrate their versatility by applying them in a plain fashion using vision, inertial and combined (vision + inertial) features as input. Results show that vision transformers are not only able to produce competitive results using only inertial data, but also can function as an architecture to fuse both modalities by means of simple concatenation, with the multimodal approach being able to produce the highest average mAP, precision and close-to-best F1-scores. Up until now, vision-based transformers have neither been explored in inertial nor in multimodal human activity recognition, making our approach the first to do so. The dataset and code to reproduce experiments is publicly available via: mariusbock.github.io/wear

Abstract: Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in Computer Vision. Indeed, Deep Learning-based models systematically struggle when applied in new scenarios never seen during training and may not be adequately tested in non-ordinary yet crucial real-world situations. This paper presents and publicly releases CrowdSim2, a new synthetic collection of images suitable for people and vehicle detection gathered from a simulator based on the Unity graphical engine. It consists of thousands of images gathered from various synthetic scenarios resembling the real world, where we varied some factors of interest, such as the weather conditions and the number of objects in the scenes. The labels are automatically collected and consist of bounding boxes that precisely localize objects belonging to the two object classes, leaving out humans from the annotation pipeline. We exploited this new benchmark as a testing ground for some state-of-the-art detectors, showing that our simulated scenarios can be a valuable tool for measuring their performances in a controlled environment.

Abstract: Two-stage object detectors generate object proposals and classify them to detect objects in images. These proposals often do not contain the objects perfectly but overlap with them in many possible ways, exhibiting great variability in the difficulty levels of the proposals. Training a robust classifier against this crop-related variability requires abundant training data, which is not available in few-shot settings. To mitigate this issue, we propose a novel variational autoencoder (VAE) based data generation model, which is capable of generating data with increased crop-related diversity. The main idea is to transform the latent space such latent codes with different norms represent different crop-related variations. This allows us to generate features with increased crop-related diversity in difficulty levels by simply varying the latent norm. In particular, each latent code is rescaled such that its norm linearly correlates with the IoU score of the input crop w.r.t. the ground-truth box. Here the IoU score is a proxy that represents the difficulty level of the crop. We train this VAE model on base classes conditioned on the semantic code of each class and then use the trained model to generate features for novel classes. In our experiments our generated features consistently improve state-of-the-art few-shot object detection methods on the PASCAL VOC and MS COCO datasets.

Abstract: Talking head generation aims to generate faces that maintain the identity information of the source image and imitate the motion of the driving image. Most pioneering methods rely primarily on 2D representations and thus will inevitably suffer from face distortion when large head rotations are encountered. Recent works instead employ explicit 3D structural representations or implicit neural rendering to improve performance under large pose changes. Nevertheless, the fidelity of identity and expression is not so desirable, especially for novel-view synthesis. In this paper, we propose HiDe-NeRF, which achieves high-fidelity and free-view talking-head synthesis. Drawing on the recently proposed Deformable Neural Radiance Fields, HiDe-NeRF represents the 3D dynamic scene into a canonical appearance field and an implicit deformation field, where the former comprises the canonical source face and the latter models the driving pose and expression. In particular, we improve fidelity from two aspects: (i) to enhance identity expressiveness, we design a generalized appearance module that leverages multi-scale volume features to preserve face shape and details; (ii) to improve expression preciseness, we propose a lightweight deformation module that explicitly decouples the pose and expression to enable precise expression modeling. Extensive experiments demonstrate that our proposed approach can generate better results than previous works. Project page: https://www.waytron.net/hidenerf/

Abstract: Adversarial attacks in the physical world can harm the robustness of detection models. Evaluating the robustness of detection models in the physical world can be challenging due to the time-consuming and labor-intensive nature of many experiments. Thus, virtual simulation experiments can provide a solution to this challenge. However, there is no unified detection benchmark based on virtual simulation environment. To address this challenge, we proposed an instant-level data generation pipeline based on the CARLA simulator. Using this pipeline, we generated the DCI dataset and conducted extensive experiments on three detection models and three physical adversarial attacks. The dataset covers 7 continuous and 1 discrete scenes, with over 40 angles, 20 distances, and 20,000 positions. The results indicate that Yolo v6 had strongest resistance, with only a 6.59% average AP drop, and ASA was the most effective attack algorithm with a 14.51% average AP reduction, twice that of other algorithms. Static scenes had higher recognition AP, and results under different weather conditions were similar. Adversarial attack algorithm improvement may be approaching its 'limitation'.

Abstract: With the rise of Deep Neural Networks, machine learning systems are nowadays ubiquitous in a number of real-world applications, which bears the need for highly reliable models. This requires a thorough look not only at the accuracy of such systems, but also to their predictive uncertainty. Hence, we propose a novel technique (with two different variations, named M-ATTA and V-ATTA) based on test time augmentation, to improve the uncertainty calibration of deep models for image classification. Unlike other test time augmentation approaches, M/V-ATTA improves uncertainty calibration without affecting the model's accuracy, by leveraging an adaptive weighting system. We evaluate the performance of the technique with respect to different metrics of uncertainty calibration. Empirical results, obtained on CIFAR-10, CIFAR-100, as well as on the benchmark Aerial Image Dataset, indicate that the proposed approach outperforms state-of-the-art calibration techniques, while maintaining the baseline classification performance. Code for M/V-ATTA available at: https://github.com/pedrormconde/MV-ATTA.

Abstract: With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more heterogeneous trajectories with different representation forms, such as 2D or 3D coordinates, 2D or 3D bounding boxes, and even high-dimensional human skeletons, need to be analyzed and forecasted. Among these heterogeneous trajectories, interactions between different elements within a frame of trajectory, which we call the ``Dimension-Wise Interactions'', would be more complex and challenging. However, most previous approaches focus mainly on a specific form of trajectories, which means these methods could not be used to forecast heterogeneous trajectories, not to mention the dimension-wise interaction. Besides, previous methods mostly treat trajectory prediction as a normal time sequence generation task, indicating that these methods may require more work to directly analyze agents' behaviors and social interactions at different temporal scales. In this paper, we bring a new ``view'' for trajectory prediction to model and forecast trajectories hierarchically according to different frequency portions from the spectral domain to learn to forecast trajectories by considering their frequency responses. Moreover, we try to expand the current trajectory prediction task by introducing the dimension $M$ from ``another view'', thus extending its application scenarios to heterogeneous trajectories vertically. Finally, we adopt the bilinear structure to fuse two factors, including the frequency response and the dimension-wise interaction, to forecast heterogeneous trajectories via spectrums hierarchically in a generic way. Experiments show that the proposed model outperforms most state-of-the-art methods on ETH-UCY, Stanford Drone Dataset and nuScenes with heterogeneous trajectories, including 2D coordinates, 2D and 3D bounding boxes.

Abstract: Video anomaly detection (VAD) is a significant computer vision problem. Existing deep neural network (DNN) based VAD methods mostly follow the route of frame reconstruction or frame prediction. However, the lack of mining and learning of higher-level visual features and temporal context relationships in videos limits the further performance of these two approaches. Inspired by video codec theory, we introduce a brand-new VAD paradigm to break through these limitations: First, we propose a new task of video event restoration based on keyframes. Encouraging DNN to infer missing multiple frames based on video keyframes so as to restore a video event, which can more effectively motivate DNN to mine and learn potential higher-level visual features and comprehensive temporal context relationships in the video. To this end, we propose a novel U-shaped Swin Transformer Network with Dual Skip Connections (USTN-DSC) for video event restoration, where a cross-attention and a temporal upsampling residual skip connection are introduced to further assist in restoring complex static and dynamic motion object features in the video. In addition, we propose a simple and effective adjacent frame difference loss to constrain the motion consistency of the video sequence. Extensive experiments on benchmarks demonstrate that USTN-DSC outperforms most existing methods, validating the effectiveness of our method.

Abstract: Bundle adjustment (BA) is the standard way to optimise camera poses and to produce sparse representations of a scene. However, as the number of camera poses and features grows, refinement through bundle adjustment becomes inefficient. Inspired by global motion averaging methods, we propose a new bundle adjustment objective which does not rely on image features' reprojection errors yet maintains precision on par with classical BA. Our method averages over relative motions while implicitly incorporating the contribution of the structure in the adjustment. To that end, we weight the objective function by local hessian matrices - a by-product of local bundle adjustments performed on relative motions (e.g., pairs or triplets) during the pose initialisation step. Such hessians are extremely rich as they encapsulate both the features' random errors and the geometric configuration between the cameras. These pieces of information propagated to the global frame help to guide the final optimisation in a more rigorous way. We argue that this approach is an upgraded version of the motion averaging approach and demonstrate its effectiveness on both photogrammetric datasets and computer vision benchmarks.

Abstract: Style transfer is the task of reproducing the semantic contents of a source image in the artistic style of a second target image. In this paper, we present NeAT, a new state-of-the art feed-forward style transfer method. We re-formulate feed-forward style transfer as image editing, rather than image generation, resulting in a model which improves over the state-of-the-art in both preserving the source content and matching the target style. An important component of our model's success is identifying and fixing "style halos", a commonly occurring artefact across many style transfer techniques. In addition to training and testing on standard datasets, we introduce the BBST-4M dataset, a new, large scale, high resolution dataset of 4M images. As a component of curating this data, we present a novel model able to classify if an image is stylistic. We use BBST-4M to improve and measure the generalization of NeAT across a huge variety of styles. Not only does NeAT offer state-of-the-art quality and generalization, it is designed and trained for fast inference at high resolution.

Abstract: Visual simultaneous localization and mapping (SLAM) systems face challenges in detecting loop closure under the circumstance of large viewpoint changes. In this paper, we present an object-based loop closure detection method based on the spatial layout and semanic consistency of the 3D scene graph. Firstly, we propose an object-level data association approach based on the semantic information from semantic labels, intersection over union (IoU), object color, and object embedding. Subsequently, multi-view bundle adjustment with the associated objects is utilized to jointly optimize the poses of objects and cameras. We represent the refined objects as a 3D spatial graph with semantics and topology. Then, we propose a graph matching approach to select correspondence objects based on the structure layout and semantic property similarity of vertices' neighbors. Finally, we jointly optimize camera trajectories and object poses in an object-level pose graph optimization, which results in a globally consistent map. Experimental results demonstrate that our proposed data association approach can construct more accurate 3D semantic maps, and our loop closure method is more robust than point-based and object-based methods in circumstances with large viewpoint changes.

Abstract: The success of transformers in computer vision has led to several attempts to adapt them for mobile devices, but their performance remains unsatisfactory in some real-world applications. To address this issue, we propose PP-MobileSeg, a semantic segmentation model that achieves state-of-the-art performance on mobile devices. PP-MobileSeg comprises three novel parts: the StrideFormer backbone, the Aggregated Attention Module (AAM), and the Valid Interpolate Module (VIM). The four-stage StrideFormer backbone is built with MV3 blocks and strided SEA attention, and it is able to extract rich semantic and detailed features with minimal parameter overhead. The AAM first filters the detailed features through semantic feature ensemble voting and then combines them with semantic features to enhance the semantic information. Furthermore, we proposed VIM to upsample the downsampled feature to the resolution of the input image. It significantly reduces model latency by only interpolating classes present in the final prediction, which is the most significant contributor to overall model latency. Extensive experiments show that PP-MobileSeg achieves a superior tradeoff between accuracy, model size, and latency compared to other methods. On the ADE20K dataset, PP-MobileSeg achieves 1.57% higher accuracy in mIoU than SeaFormer-Base with 32.9% fewer parameters and 42.3% faster acceleration on Qualcomm Snapdragon 855. Source codes are available at https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.8.

Abstract: Deep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, predict categorical labels, whereas biomarkers are often continuous measurements. We hypothesized that regression-based DL outperforms classification-based DL. Therefore, we developed and evaluated a new self-supervised attention-based weakly supervised regression method that predicts continuous biomarkers directly from images in 11,671 patients across nine cancer types. We tested our method for multiple clinically and biologically relevant biomarkers: homologous repair deficiency (HRD) score, a clinically used pan-cancer biomarker, as well as markers of key biological processes in the tumor microenvironment. Using regression significantly enhances the accuracy of biomarker prediction, while also improving the interpretability of the results over classification. In a large cohort of colorectal cancer patients, regression-based prediction scores provide a higher prognostic value than classification-based scores. Our open-source regression approach offers a promising alternative for continuous biomarker analysis in computational pathology.

Abstract: Branch-and-bound-based consensus maximization stands out due to its important ability of retrieving the globally optimal solution to outlier-affected geometric problems. However, while the discovery of such solutions caries high scientific value, its application in practical scenarios is often prohibited by its computational complexity growing exponentially as a function of the dimensionality of the problem at hand. In this work, we convey a novel, general technique that allows us to branch over an $n-1$ dimensional space for an n-dimensional problem. The remaining degree of freedom can be solved globally optimally within each bound calculation by applying the efficient interval stabbing technique. While each individual bound derivation is harder to compute owing to the additional need for solving a sorting problem, the reduced number of intervals and tighter bounds in practice lead to a significant reduction in the overall number of required iterations. Besides an abstract introduction of the approach, we present applications to three fundamental geometric computer vision problems: camera resectioning, relative camera pose estimation, and point set registration. Through our exhaustive tests, we demonstrate significant speed-up factors at times exceeding two orders of magnitude, thereby increasing the viability of globally optimal consensus maximizers in online application scenarios.

Abstract: Is self-supervised deep learning (DL) for medical image analysis already a serious alternative to the de facto standard of end-to-end trained supervised DL? We tackle this question for medical image classification, with a particular focus on one of the currently most limiting factors of the field: the (non-)availability of labeled data. Based on three common medical imaging modalities (bone marrow microscopy, gastrointestinal endoscopy, dermoscopy) and publicly available data sets, we analyze the performance of self-supervised DL within the self-distillation with no labels (DINO) framework. After learning an image representation without use of image labels, conventional machine learning classifiers are applied. The classifiers are fit using a systematically varied number of labeled data (1-1000 samples per class). Exploiting the learned image representation, we achieve state-of-the-art classification performance for all three imaging modalities and data sets with only a fraction of between 1% and 10% of the available labeled data and about 100 labeled samples per class.

Abstract: Multi-object tracking in sports scenes plays a critical role in gathering players statistics, supporting further analysis, such as automatic tactical analysis. Yet existing MOT benchmarks cast little attention on the domain, limiting its development. In this work, we present a new large-scale multi-object tracking dataset in diverse sports scenes, coined as \emph{SportsMOT}, where all players on the court are supposed to be tracked. It consists of 240 video sequences, over 150K frames (almost 15\times MOT17) and over 1.6M bounding boxes (3\times MOT17) collected from 3 sports categories, including basketball, volleyball and football. Our dataset is characterized with two key properties: 1) fast and variable-speed motion and 2) similar yet distinguishable appearance. We expect SportsMOT to encourage the MOT trackers to promote in both motion-based association and appearance-based association. We benchmark several state-of-the-art trackers and reveal the key challenge of SportsMOT lies in object association. To alleviate the issue, we further propose a new multi-object tracking framework, termed as \emph{MixSort}, introducing a MixFormer-like structure as an auxiliary association model to prevailing tracking-by-detection trackers. By integrating the customized appearance-based association with the original motion-based association, MixSort achieves state-of-the-art performance on SportsMOT and MOT17. Based on MixSort, we give an in-depth analysis and provide some profound insights into SportsMOT. The dataset and code will be available at https://deeperaction.github.io/datasets/sportsmot.html.

Abstract: Deep learning based fusion methods have been achieving promising performance in image fusion tasks. This is attributed to the network architecture that plays a very important role in the fusion process. However, in general, it is hard to specify a good fusion architecture, and consequently, the design of fusion networks is still a black art, rather than science. To address this problem, we formulate the fusion task mathematically, and establish a connection between its optimal solution and the network architecture that can implement it. This approach leads to a novel method proposed in the paper of constructing a lightweight fusion network. It avoids the time-consuming empirical network design by a trial-and-test strategy. In particular we adopt a learnable representation approach to the fusion task, in which the construction of the fusion network architecture is guided by the optimisation algorithm producing the learnable model. The low-rank representation (LRR) objective is the foundation of our learnable model. The matrix multiplications, which are at the heart of the solution are transformed into convolutional operations, and the iterative process of optimisation is replaced by a special feed-forward network. Based on this novel network architecture, an end-to-end lightweight fusion network is constructed to fuse infrared and visible light images. Its successful training is facilitated by a detail-to-semantic information loss function proposed to preserve the image details and to enhance the salient features of the source images. Our experiments show that the proposed fusion network exhibits better fusion performance than the state-of-the-art fusion methods on public datasets. Interestingly, our network requires a fewer training parameters than other existing methods.

Abstract: Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the visual input from an external memory set. In this work, we introduce an attention-based memory module, which learns the importance of each retrieved example from the memory. Compared to existing approaches, our method removes the influence of the irrelevant retrieved examples, and retains those that are beneficial to the input query. We also thoroughly study various ways of constructing the memory dataset. Our experiments show the benefit of using a massive-scale memory dataset of 1B image-text pairs, and demonstrate the performance of different memory representations. We evaluate our method in three different classification tasks, namely long-tailed recognition, learning with noisy labels, and fine-grained classification, and show that it achieves state-of-the-art accuracies in ImageNet-LT, Places-LT and Webvision datasets.

Abstract: In this work, we developed a wearable, head-mounted device that automatically calculates the precise Relative Afferent Pupillary Defect (RAPD) value of a patient. The device consists of two RGB LEDs, two infrared cameras, and one microcontroller. In the RAPD test, the parameters like LED on-off durations, brightness level, and color of the light can be controlled by the user. Upon data acquisition, a computational unit processes the data, calculates the RAPD score and visualizes the test results with a user-friendly interface.Multiprocessing methods used on GUI to optimize the processing pipeline. We have shown that our head-worn instrument is easy to use, fast, and suitable for early-diagnostics and screening purposes for various neurological conditions such as RAPD, glaucoma, asymmetric glaucoma, and anisocoria.

Abstract: Rolling bearings are critical components in rotating machinery, and their faults can cause severe damage. Early detection of abnormalities is crucial to prevent catastrophic accidents. Traditional and intelligent methods have been used to analyze time series data, but in real-life scenarios, sensor data is often noisy and cannot be accurately characterized in the time domain, leading to mode collapse in trained models. Two-dimensionalization methods such as the Gram angle field method (GAF) or interval sampling have been proposed, but they lack mathematical derivation and interpretability. This paper proposes an improved GAF combined with grayscale images for convolution scenarios. The main contributions include illustrating the feasibility of the approach in complex scenarios, widening the data set, and introducing an improved convolutional neural network method with a multi-scale feature fusion diffusion model and deep learning compression techniques for deployment in industrial scenarios.

Abstract: Classification of AI-manipulated content is receiving great attention, for distinguishing different types of manipulations. Most of the methods developed so far fail in the open-set scenario, that is when the algorithm used for the manipulation is not represented by the training set. In this paper, we focus on the classification of synthetic face generation and manipulation in open-set scenarios, and propose a method for classification with a rejection option. The proposed method combines the use of Vision Transformers (ViT) with a hybrid approach for simultaneous classification and localization. Feature map correlation is exploited by the ViT module, while a localization branch is employed as an attention mechanism to force the model to learn per-class discriminative features associated with the forgery when the manipulation is performed locally in the image. Rejection is performed by considering several strategies and analyzing the model output layers. The effectiveness of the proposed method is assessed for the task of classification of facial attribute editing and GAN attribution.

Abstract: As the potential of foundation models in visual tasks has garnered significant attention, pretraining these models before downstream tasks has become a crucial step. The three key factors in pretraining foundation models are the pretraining method, the size of the pretraining dataset, and the number of model parameters. Recently, research in the remote sensing field has focused primarily on the pretraining method and the size of the dataset, with limited emphasis on the number of model parameters. This paper addresses this gap by examining the effect of increasing the number of model parameters on the performance of foundation models in downstream tasks such as rotated object detection and semantic segmentation. We pretrained foundation models with varying numbers of parameters, including 86M, 605.26M, 1.3B, and 2.4B, to determine whether performance in downstream tasks improved with an increase in parameters. To the best of our knowledge, this is the first billion-scale foundation model in the remote sensing field. Furthermore, we propose an effective method for scaling up and fine-tuning a vision transformer in the remote sensing field. To evaluate general performance in downstream tasks, we employed the DOTA v2.0 and DIOR-R benchmark datasets for rotated object detection, and the Potsdam and LoveDA datasets for semantic segmentation. Experimental results demonstrated that, across all benchmark datasets and downstream tasks, the performance of the foundation models and data efficiency improved as the number of parameters increased. Moreover, our models achieve the state-of-the-art performance on several datasets including DIOR-R, Postdam, and LoveDA.

Abstract: With dense inputs, Neural Radiance Fields (NeRF) is able to render photo-realistic novel views under static conditions. Although the synthesis quality is excellent, existing NeRF-based methods fail to obtain moderate three-dimensional (3D) structures. The novel view synthesis quality drops dramatically given sparse input due to the implicitly reconstructed inaccurate 3D-scene structure. We propose SfMNeRF, a method to better synthesize novel views as well as reconstruct the 3D-scene geometry. SfMNeRF leverages the knowledge from the self-supervised depth estimation methods to constrain the 3D-scene geometry during view synthesis training. Specifically, SfMNeRF employs the epipolar, photometric consistency, depth smoothness, and position-of-matches constraints to explicitly reconstruct the 3D-scene structure. Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time. In addition, SfMNeRF synthesizes novel sub-pixels in which the ground truth is obtained by image interpolation. This strategy enables SfMNeRF to include more samples to improve generalization performance. Experiments on two public datasets demonstrate that SfMNeRF surpasses state-of-the-art approaches. Code is available at https://github.com/XTU-PR-LAB/SfMNeRF

Abstract: We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A na\"ive approach to incremental object counting would suffer from catastrophic forgetting, where it would suffer from a dramatic performance drop on previous tasks. In this paper, we propose a new exemplar-free functional regularization method, called Density Map Distillation (DMD). During training, we introduce a new counter head for each task and introduce a distillation loss to prevent forgetting of previous tasks. Additionally, we introduce a cross-task adaptor that projects the features of the current backbone to the previous backbone. This projector allows for the learning of new features while the backbone retains the relevant features for previous tasks. Finally, we set up experiments of incremental learning for counting new objects. Results confirm that our method greatly reduces catastrophic forgetting and outperforms existing methods.

Abstract: The recent large-scale generative modeling has attained unprecedented performance especially in producing high-fidelity images driven by text prompts. Text inversion (TI), alongside the text-to-image model backbones, is proposed as an effective technique in personalizing the generation when the prompts contain user-defined, unseen or long-tail concept tokens. Despite that, we find and show that the deployment of TI remains full of "dark-magics" -- to name a few, the harsh requirement of additional datasets, arduous human efforts in the loop and lack of robustness. In this work, we propose a much-enhanced version of TI, dubbed Controllable Textual Inversion (COTI), in resolving all the aforementioned problems and in turn delivering a robust, data-efficient and easy-to-use framework. The core to COTI is a theoretically-guided loss objective instantiated with a comprehensive and novel weighted scoring mechanism, encapsulated by an active-learning paradigm. The extensive results show that COTI significantly outperforms the prior TI-related approaches with a 26.05 decrease in the FID score and a 23.00% boost in the R-precision.

Abstract: Understanding the road genome is essential to realize autonomous driving. This highly intelligent problem contains two aspects - the connection relationship of lanes, and the assignment relationship between lanes and traffic elements, where a comprehensive topology reasoning method is vacant. On one hand, previous map learning techniques struggle in deriving lane connectivity with segmentation or laneline paradigms; or prior lane topology-oriented approaches focus on centerline detection and neglect the interaction modeling. On the other hand, the traffic element to lane assignment problem is limited in the image domain, leaving how to construct the correspondence from two views an unexplored challenge. To address these issues, we present TopoNet, the first end-to-end framework capable of abstracting traffic knowledge beyond conventional perception tasks. To capture the driving scene topology, we introduce three key designs: (1) an embedding module to incorporate semantic knowledge from 2D elements into a unified feature space; (2) a curated scene graph neural network to model relationships and enable feature interaction inside the network; (3) instead of transmitting messages arbitrarily, a scene knowledge graph is devised to differentiate prior knowledge from various types of the road genome. We evaluate TopoNet on the challenging scene understanding benchmark, OpenLane-V2, where our approach outperforms all previous works by a great margin on all perceptual and topological metrics. The code would be released soon.

Abstract: Deep machine learning models including Convolutional Neural Networks (CNN) have been successful in the detection of Mild Cognitive Impairment (MCI) using medical images, questionnaires, and videos. This paper proposes a novel Multi-branch Classifier-Video Vision Transformer (MC-ViViT) model to distinguish MCI from those with normal cognition by analyzing facial features. The data comes from the I-CONECT, a behavioral intervention trial aimed at improving cognitive function by providing frequent video chats. MC-ViViT extracts spatiotemporal features of videos in one branch and augments representations by the MC module. The I-CONECT dataset is challenging as the dataset is imbalanced containing Hard-Easy and Positive-Negative samples, which impedes the performance of MC-ViViT. We propose a loss function for Hard-Easy and Positive-Negative Samples (HP Loss) by combining Focal loss and AD-CORRE loss to address the imbalanced problem. Our experimental results on the I-CONECT dataset show the great potential of MC-ViViT in predicting MCI with a high accuracy of 90.63\% accuracy on some of the interview videos.

Abstract: Object detection is a crucial task in computer vision that aims to identify and localize objects in images or videos. The recent advancements in deep learning and Convolutional Neural Networks (CNNs) have significantly improved the performance of object detection techniques. This paper presents a comprehensive study of object detection techniques in unconstrained environments, including various challenges, datasets, and state-of-the-art approaches. Additionally, we present a comparative analysis of the methods and highlight their strengths and weaknesses. Finally, we provide some future research directions to further improve object detection in unconstrained environments.

Abstract: 3D reconstruction from multiple views is a successful computer vision field with multiple deployments in applications. State of the art is based on traditional RGB frames that enable optimization of photo-consistency cross views. In this paper, we study the problem of 3D reconstruction from event-cameras, motivated by the advantages of event-based cameras in terms of low power and latency as well as by the biological evidence that eyes in nature capture the same data and still perceive well 3D shape. The foundation of our hypothesis that 3D reconstruction is feasible using events lies in the information contained in the occluding contours and in the continuous scene acquisition with events. We propose Apparent Contour Events (ACE), a novel event-based representation that defines the geometry of the apparent contour of an object. We represent ACE by a spatially and temporally continuous implicit function defined in the event x-y-t space. Furthermore, we design a novel continuous Voxel Carving algorithm enabled by the high temporal resolution of the Apparent Contour Events. To evaluate the performance of the method, we collect MOEC-3D, a 3D event dataset of a set of common real-world objects. We demonstrate the ability of EvAC3D to reconstruct high-fidelity mesh surfaces from real event sequences while allowing the refinement of the 3D reconstruction for each individual event.

Abstract: The paper presents a modular approach for the estimation of a leading vehicle's velocity based on a non-intrusive stereo camera where SiamMask is used for leading vehicle tracking, Kernel Density estimate (KDE) is used to smooth the distance prediction from a disparity map, and LightGBM is used for leading vehicle velocity estimation. Our approach yields an RMSE of 0.416 which outperforms the baseline RMSE of 0.582 for the SUBARU Image Recognition Challenge

Abstract: Deep learning has shown great potential in assisting radiologists in reading chest X-ray (CXR) images, but its need for expensive annotations for improving performance prevents widespread clinical application. Visual language pre-training (VLP) can alleviate the burden and cost of annotation by leveraging routinely generated reports for radiographs, which exist in large quantities as well as in paired form (imagetext pairs). Additionally, extensions to localization-aware VLPs are being proposed to address the needs of accurate localization of abnormalities for CAD in CXR. However, we find that the formulation proposed by locality-aware VLP literatures actually leads to loss in spatial relationships required for downstream localization tasks. Therefore, we propose Empowering Locality of VLP with Intra-modal Similarity, ELVIS, a VLP aware of intra-modal locality, to better preserve the locality within radiographs or reports, which enhances the ability to comprehend location references in text reports. Our locality-aware VLP method significantly outperforms state-of-the art baselines in multiple segmentation tasks and the MS-CXR phrase grounding task. Qualitatively, ELVIS is able to focus well on regions of interest described in the report text compared to prior approaches, allowing for enhanced interpretability.

Abstract: The vision-based perception for autonomous driving has undergone a transformation from the bird-eye-view (BEV) representations to the 3D semantic occupancy. Compared with the BEV planes, the 3D semantic occupancy further provides structural information along the vertical direction. This paper presents OccFormer, a dual-path transformer network to effectively process the 3D volume for semantic occupancy prediction. OccFormer achieves a long-range, dynamic, and efficient encoding of the camera-generated 3D voxel features. It is obtained by decomposing the heavy 3D processing into the local and global transformer pathways along the horizontal plane. For the occupancy decoder, we adapt the vanilla Mask2Former for 3D semantic occupancy by proposing preserve-pooling and class-guided sampling, which notably mitigate the sparsity and class imbalance. Experimental results demonstrate that OccFormer significantly outperforms existing methods for semantic scene completion on SemanticKITTI dataset and for LiDAR semantic segmentation on nuScenes dataset. Code is available at \url{https://github.com/zhangyp15/OccFormer}.

Abstract: Multi-modal medical images provide complementary soft-tissue characteristics that aid in the screening and diagnosis of diseases. However, limited scanning time, image corruption and various imaging protocols often result in incomplete multi-modal images, thus limiting the usage of multi-modal data for clinical purposes. To address this issue, in this paper, we propose a novel unified multi-modal image synthesis method for missing modality imputation. Our method overall takes a generative adversarial architecture, which aims to synthesize missing modalities from any combination of available ones with a single model. To this end, we specifically design a Commonality- and Discrepancy-Sensitive Encoder for the generator to exploit both modality-invariant and specific information contained in input modalities. The incorporation of both types of information facilitates the generation of images with consistent anatomy and realistic details of the desired distribution. Besides, we propose a Dynamic Feature Unification Module to integrate information from a varying number of available modalities, which enables the network to be robust to random missing modalities. The module performs both hard integration and soft integration, ensuring the effectiveness of feature combination while avoiding information loss. Verified on two public multi-modal magnetic resonance datasets, the proposed method is effective in handling various synthesis tasks and shows superior performance compared to previous methods.

Abstract: Nowadays, the deployment of deep learning based applications on edge devices is an essential task owing to the increasing demands on intelligent services. However, the limited computing resources on edge nodes make the models vulnerable to attacks, such that the predictions made by models are unreliable. In this paper, we investigate latency attacks on deep learning applications. Unlike common adversarial attacks for misclassification, the goal of latency attacks is to increase the inference time, which may stop applications from responding to the requests within a reasonable time. This kind of attack is ubiquitous for various applications, and we use object detection to demonstrate how such kind of attacks work. We also design a framework named Overload to generate latency attacks at scale. Our method is based on a newly formulated optimization problem and a novel technique, called spatial attention, to increase the inference time of object detection. We have conducted experiments using YOLOv5 models on Nvidia NX. The experimental results show that with latency attacks, the inference time of a single image can be increased ten times longer in reference to the normal setting. Moreover, comparing to existing methods, our attacking method is simpler and more effective.

Abstract: We tackle the challenging task of unsupervised object localization in this work. Recently, transformers trained with self-supervised learning have been shown to exhibit object localization properties without being trained for this task. In this work, we present Multiple Object localization with Self-supervised Transformers (MOST) that uses features of transformers trained using self-supervised learning to localize multiple objects in real world images. MOST analyzes the similarity maps of the features using box counting; a fractal analysis tool to identify tokens lying on foreground patches. The identified tokens are then clustered together, and tokens of each cluster are used to generate bounding boxes on foreground regions. Unlike recent state-of-the-art object localization methods, MOST can localize multiple objects per image and outperforms SOTA algorithms on several object localization and discovery benchmarks on PASCAL-VOC 07, 12 and COCO20k datasets. Additionally, we show that MOST can be used for self-supervised pre-training of object detectors, and yields consistent improvements on fully, semi-supervised object detection and unsupervised region proposal generation.

Abstract: In recent years, Text-to-Image (T2I) models have been extensively studied, especially with the emergence of diffusion models that achieve state-of-the-art results on T2I synthesis tasks. However, existing benchmarks heavily rely on subjective human evaluation, limiting their ability to holistically assess the model's capabilities. Furthermore, there is a significant gap between efforts in developing new T2I architectures and those in evaluation. To address this, we introduce HRS-Bench, a concrete evaluation benchmark for T2I models that is Holistic, Reliable, and Scalable. Unlike existing bench-marks that focus on limited aspects, HRS-Bench measures 13 skills that can be categorized into five major categories: accuracy, robustness, generalization, fairness, and bias. In addition, HRS-Bench covers 50 scenarios, including fashion, animals, transportation, food, and clothes. We evaluate nine recent large-scale T2I models using metrics that cover a wide range of skills. A human evaluation aligned with 95% of our evaluations on average was conducted to probe the effectiveness of HRS-Bench. Our experiments demonstrate that existing models often struggle to generate images with the desired count of objects, visual text, or grounded emotions. We hope that our benchmark help ease future text-to-image generation research. The code and data are available at https://eslambakr.github.io/hrsbench.github.io

Abstract: Despite impressive advances in object-recognition, deep learning systems' performance degrades significantly across geographies and lower income levels raising pressing concerns of inequity. Addressing such performance gaps remains a challenge, as little is understood about why performance degrades across incomes or geographies. We take a step in this direction by annotating images from Dollar Street, a popular benchmark of geographically and economically diverse images, labeling each image with factors such as color, shape, and background. These annotations unlock a new granular view into how objects differ across incomes and regions. We then use these object differences to pinpoint model vulnerabilities across incomes and regions. We study a range of modern vision models, finding that performance disparities are most associated with differences in texture, occlusion, and images with darker lighting. We illustrate how insights from our factor labels can surface mitigations to improve models' performance disparities. As an example, we show that mitigating a model's vulnerability to texture can improve performance on the lower income level. We release all the factor annotations along with an interactive dashboard to facilitate research into more equitable vision systems.