Computer Vision and Pattern Recognition (cs.CV)

Abstract: In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represented by local body parts, such as legs or hands, which are advantageous for skeleton-based action recognition. This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action representations. To achieve this, a multi-head attention mask module is employed to learn the soft attention mask features from the skeletons, suppressing non-salient local features while accentuating local salient features, thereby bringing similar local features closer in the feature space. Additionally, ample contrastive pairs are generated by expanding contrastive pairs based on salient and non-salient features with global features, which guide the network to learn the semantic representations of the entire skeleton. Therefore, with the attention mask mechanism, SkeAttnCLR learns local features under different data augmentation views. The experiment results demonstrate that the inclusion of local feature similarity significantly enhances skeleton-based action representation. Our proposed SkeAttnCLR outperforms state-of-the-art methods on NTURGB+D, NTU120-RGB+D, and PKU-MMD datasets.

Abstract: The lightweight MLP-based decoder has become increasingly promising for semantic segmentation. However, the channel-wise MLP cannot expand the receptive fields, lacking the context modeling capacity, which is critical to semantic segmentation. In this paper, we propose a parametric-free patch rotate operation to reorganize the pixels spatially. It first divides the feature map into multiple groups and then rotates the patches within each group. Based on the proposed patch rotate operation, we design a novel segmentation network, named PRSeg, which includes an off-the-shelf backbone and a lightweight Patch Rotate MLP decoder containing multiple Dynamic Patch Rotate Blocks (DPR-Blocks). In each DPR-Block, the fully connected layer is performed following a Patch Rotate Module (PRM) to exchange spatial information between pixels. Specifically, in PRM, the feature map is first split into the reserved part and rotated part along the channel dimension according to the predicted probability of the Dynamic Channel Selection Module (DCSM), and our proposed patch rotate operation is only performed on the rotated part. Extensive experiments on ADE20K, Cityscapes and COCO-Stuff 10K datasets prove the effectiveness of our approach. We expect that our PRSeg can promote the development of MLP-based decoder in semantic segmentation.

Abstract: In semi-supervised medical image segmentation, there exist empirical mismatch problems between labeled and unlabeled data distribution. The knowledge learned from the labeled data may be largely discarded if treating labeled and unlabeled data separately or in an inconsistent manner. We propose a straightforward method for alleviating the problem - copy-pasting labeled and unlabeled data bidirectionally, in a simple Mean Teacher architecture. The method encourages unlabeled data to learn comprehensive common semantics from the labeled data in both inward and outward directions. More importantly, the consistent learning procedure for labeled and unlabeled data can largely reduce the empirical distribution gap. In detail, we copy-paste a random crop from a labeled image (foreground) onto an unlabeled image (background) and an unlabeled image (foreground) onto a labeled image (background), respectively. The two mixed images are fed into a Student network and supervised by the mixed supervisory signals of pseudo-labels and ground-truth. We reveal that the simple mechanism of copy-pasting bidirectionally between labeled and unlabeled data is good enough and the experiments show solid gains (e.g., over 21% Dice improvement on ACDC dataset with 5% labeled data) compared with other state-of-the-arts on various semi-supervised medical image segmentation datasets. Code is available at https://github.com/DeepMed-Lab-ECNU/BCP}.

Abstract: Although lane detection methods have shown impressive performance in real-world scenarios, most of methods require post-processing which is not robust enough. Therefore, end-to-end detectors like DEtection TRansformer(DETR) have been introduced in lane detection. However, one-to-one label assignment in DETR can degrade the training efficiency due to label semantic conflicts. Besides, positional query in DETR is unable to provide explicit positional prior, making it difficult to be optimized. In this paper, we present the One-to-Several Transformer(O2SFormer). We first propose the one-to-several label assignment, which combines one-to-one and one-to-many label assignments to improve the training efficiency while keeping end-to-end detection. To overcome the difficulty in optimizing one-to-one assignment. We further propose the layer-wise soft label which adjusts the positive weight of positive lane anchors across different decoder layers. Finally, we design the dynamic anchor-based positional query to explore positional prior by incorporating lane anchors into positional query. Experimental results show that O2SFormer significantly speeds up the convergence of DETR and outperforms Transformer-based and CNN-based detectors on the CULane dataset. Code will be available athttps://github.com/zkyseu/O2SFormer.

Abstract: Medical image segmentation is a fundamental task in the community of medical image analysis. In this paper, a novel network architecture, referred to as Convolution, Transformer, and Operator (CTO), is proposed. CTO employs a combination of Convolutional Neural Networks (CNNs), Vision Transformer (ViT), and an explicit boundary detection operator to achieve high recognition accuracy while maintaining an optimal balance between accuracy and efficiency. The proposed CTO follows the standard encoder-decoder segmentation paradigm, where the encoder network incorporates a popular CNN backbone for capturing local semantic information, and a lightweight ViT assistant for integrating long-range dependencies. To enhance the learning capacity on boundary, a boundary-guided decoder network is proposed that uses a boundary mask obtained from a dedicated boundary detection operator as explicit supervision to guide the decoding learning process. The performance of the proposed method is evaluated on six challenging medical image segmentation datasets, demonstrating that CTO achieves state-of-the-art accuracy with a competitive model complexity.

Abstract: Very high-resolution (VHR) remote sensing (RS) scene classification is a challenging task due to the higher inter-class similarity and intra-class variability problems. Recently, the existing deep learning (DL)-based methods have shown great promise in VHR RS scene classification. However, they still provide an unstable classification performance. To address such a problem, we, in this letter, propose a novel DL-based approach. For this, we devise an enhanced VHR attention module (EAM), followed by the atrous spatial pyramid pooling (ASPP) and global average pooling (GAP). This procedure imparts the enhanced features from the corresponding level. Then, the multi-level feature fusion is performed. Experimental results on two widely-used VHR RS datasets show that the proposed approach yields a competitive and stable/robust classification performance with the least standard deviation of 0.001. Further, the highest overall accuracies on the AID and the NWPU datasets are 95.39% and 93.04%, respectively.

Abstract: Cameras digitize real-world scenes as pixel intensity values with a limited value range given by the available bits per pixel (bpp). High Dynamic Range (HDR) cameras capture those luminance values in higher resolution through an increase in the number of bpp. Most displays, however, are limited to 8 bpp. Naive HDR compression methods lead to a loss of the rich information contained in those HDR images. In this paper, tone mapping algorithms for thermal infrared images with 16 bpp are investigated that can preserve this information. An optimized multi-scale Retinex algorithm sets the baseline. This algorithm is then approximated with a deep learning approach based on the popular U-Net architecture. The remaining noise in the images after tone mapping is reduced implicitly by utilizing a self-supervised deep learning approach that can be jointly trained with the tone mapping approach in a multi-task learning scheme. Further discussions are provided on denoising and deflickering for thermal infrared video enhancement in the context of tone mapping. Extensive experiments on the public FLIR ADAS Dataset prove the effectiveness of our proposed method in comparison with the state-of-the-art.

Abstract: Digital pathology based on whole slide images (WSIs) plays a key role in cancer diagnosis and clinical practice. Due to the high resolution of the WSI and the unavailability of patch-level annotations, WSI classification is usually formulated as a weakly supervised problem, which relies on multiple instance learning (MIL) based on patches of a WSI. In this paper, we aim to learn an optimal patch-level feature space by integrating prototype learning with MIL. To this end, we develop a Trainable Prototype enhanced deep MIL (TPMIL) framework for weakly supervised WSI classification. In contrast to the conventional methods which rely on a certain number of selected patches for feature space refinement, we softly cluster all the instances by allocating them to their corresponding prototypes. Additionally, our method is able to reveal the correlations between different tumor subtypes through distances between corresponding trained prototypes. More importantly, TPMIL also enables to provide a more accurate interpretability based on the distance of the instances from the trained prototypes which serves as an alternative to the conventional attention score-based interpretability. We test our method on two WSI datasets and it achieves a new SOTA. GitHub repository: https://github.com/LitaoYang-Jet/TPMIL

Abstract: The problem of organizing and finding images in a user's directory has become increasingly challenging due to the rapid growth in the number of images captured on personal devices. This paper presents a solution that utilizes zero shot learning to create image queries with only user provided text descriptions. The paper's primary contribution is the development of an algorithm that utilizes pre-trained models to extract features from images. The algorithm uses OWL to check for the presence of bounding boxes and sorts images based on cosine similarity scores. The algorithm's output is a list of images sorted in descending order of similarity, helping users to locate specific images more efficiently. The paper's experiments were conducted using a custom dataset to simulate a user's image directory and evaluated the accuracy, inference time, and size of the models. The results showed that the VGG model achieved the highest accuracy, while the Resnet50 and InceptionV3 models had the lowest inference time and size. The papers proposed algorithm provides an effective and efficient solution for organizing and finding images in a users local directory. The algorithm's performance and flexibility make it suitable for various applications, including personal image organization and search engines. Code and dataset for zero-search are available at: https://github.com/NainaniJatinZ/zero-search

Abstract: Multi-view subspace clustering methods have employed learned self-representation tensors from different tensor decompositions to exploit low rank information. However, the data structures embedded with self-representation tensors may vary in different multi-view datasets. Therefore, a pre-defined tensor decomposition may not fully exploit low rank information for a certain dataset, resulting in sub-optimal multi-view clustering performance. To alleviate the aforementioned limitations, we propose the adaptively topological tensor network (ATTN) by determining the edge ranks from the structural information of the self-representation tensor, and it can give a better tensor representation with the data-driven strategy. Specifically, in multi-view tensor clustering, we analyze the higher-order correlations among different modes of a self-representation tensor, and prune the links of the weakly correlated ones from a fully connected tensor network. Therefore, the newly obtained tensor networks can efficiently explore the essential clustering information with self-representation with different tensor structures for various datasets. A greedy adaptive rank-increasing strategy is further applied to improve the capture capacity of low rank structure. We apply ATTN on multi-view subspace clustering and utilize the alternating direction method of multipliers to solve it. Experimental results show that multi-view subspace clustering based on ATTN outperforms the counterparts on six multi-view datasets.

Abstract: The human eye consists of two types of photoreceptors, rods and cones. Rods are responsible for monochrome vision, and cones for color vision. The number of rods is much higher than the cones, which means that most human vision processing is done in monochrome. An event camera reports the change in pixel intensity and is analogous to rods. Event and color cameras in computer vision are like rods and cones in human vision. Humans can notice objects moving in the peripheral vision (far right and left), but we cannot classify them (think of someone passing by on your far left or far right, this can trigger your attention without knowing who they are). Thus, rods act as a region proposal network (RPN) in human vision. Therefore, an event camera can act as a region proposal network in deep learning Two-stage object detectors in deep learning, such as Mask R-CNN, consist of a backbone for feature extraction and a RPN. Currently, RPN uses the brute force method by trying out all the possible bounding boxes to detect an object. This requires much computation time to generate region proposals making two-stage detectors inconvenient for fast applications. This work replaces the RPN in Mask-RCNN of detectron2 with an event camera for generating proposals for moving objects. Thus, saving time and being computationally less expensive. The proposed approach is faster than the two-stage detectors with comparable accuracy

Abstract: We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision Transformers (ViTs) have the following properties: (1) CL trains self-attentions to capture longer-range global patterns than MIM, such as the shape of an object, especially in the later layers of the ViT architecture. This CL property helps ViTs linearly separate images in their representation spaces. However, it also makes the self-attentions collapse into homogeneity for all query tokens and heads. Such homogeneity of self-attention reduces the diversity of representations, worsening scalability and dense prediction performance. (2) CL utilizes the low-frequency signals of the representations, but MIM utilizes high-frequencies. Since low- and high-frequency information respectively represent shapes and textures, CL is more shape-oriented and MIM more texture-oriented. (3) CL plays a crucial role in the later layers, while MIM mainly focuses on the early layers. Upon these analyses, we find that CL and MIM can complement each other and observe that even the simplest harmonization can help leverage the advantages of both methods. The code is available at https://github.com/naver-ai/cl-vs-mim.

Abstract: Limited training data and severe class imbalance impose significant challenges to developing clinically robust deep learning models. Federated learning (FL) addresses the former by enabling different medical clients to collaboratively train a deep model without sharing data. However, the class imbalance problem persists due to inter-client class distribution variations. To overcome this, we propose federated classifier anchoring (FCA) by adding a personalized classifier at each client to guide and debias the federated model through consistency learning. Additionally, FCA debiases the federated classifier and each client's personalized classifier based on their respective class distributions, thus mitigating divergence. With FCA, the federated feature extractor effectively learns discriminative features suitably globally for federation as well as locally for all participants. In clinical practice, the federated model is expected to be both generalized, performing well across clients, and specialized, benefiting each individual client from collaboration. According to this, we propose a novel evaluation metric to assess models' generalization and specialization performance globally on an aggregated public test set and locally at each client. Through comprehensive comparison and evaluation, FCA outperforms the state-of-the-art methods with large margins for federated long-tailed skin lesion classification and intracranial hemorrhage classification, making it a more feasible solution in clinical settings.

Abstract: In recent years, raw video denoising has garnered increased attention due to the consistency with the imaging process and well-studied noise modeling in the raw domain. However, two problems still hinder the denoising performance. Firstly, there is no large dataset with realistic motions for supervised raw video denoising, as capturing noisy and clean frames for real dynamic scenes is difficult. To address this, we propose recapturing existing high-resolution videos displayed on a 4K screen with high-low ISO settings to construct noisy-clean paired frames. In this way, we construct a video denoising dataset (named as ReCRVD) with 120 groups of noisy-clean videos, whose ISO values ranging from 1600 to 25600. Secondly, while non-local temporal-spatial attention is beneficial for denoising, it often leads to heavy computation costs. We propose an efficient raw video denoising transformer network (RViDeformer) that explores both short and long-distance correlations. Specifically, we propose multi-branch spatial and temporal attention modules, which explore the patch correlations from local window, local low-resolution window, global downsampled window, and neighbor-involved window, and then they are fused together. We employ reparameterization to reduce computation costs. Our network is trained in both supervised and unsupervised manners, achieving the best performance compared with state-of-the-art methods. Additionally, the model trained with our proposed dataset (ReCRVD) outperforms the model trained with previous benchmark dataset (CRVD) when evaluated on the real-world outdoor noisy videos. Our code and dataset will be released after the acceptance of this work.

Abstract: Semantic segmentation is an important and well-known task in the field of computer vision, in which we attempt to assign a corresponding semantic class to each input element. When it comes to semantic segmentation of 2D images, the input elements are pixels. On the other hand, the input can also be a point cloud, where one input element represents one point in the input point cloud. By the term point cloud, we refer to a set of points defined by spatial coordinates with respect to some reference coordinate system. In addition to the position of points in space, other features can also be defined for each point, such as RGB components. In this paper, we conduct semantic segmentation on the S3DIS dataset, where each point cloud represents one room. We train models on the S3DIS dataset, namely PointCNN, PointNet++, Cylinder3D, Point Transformer, and RepSurf. We compare the obtained results with respect to standard evaluation metrics for semantic segmentation and present a comparison of the models based on inference speed.

Abstract: Generating talking person portraits with arbitrary speech audio is a crucial problem in the field of digital human and metaverse. A modern talking face generation method is expected to achieve the goals of generalized audio-lip synchronization, good video quality, and high system efficiency. Recently, neural radiance field (NeRF) has become a popular rendering technique in this field since it could achieve high-fidelity and 3D-consistent talking face generation with a few-minute-long training video. However, there still exist several challenges for NeRF-based methods: 1) as for the lip synchronization, it is hard to generate a long facial motion sequence of high temporal consistency and audio-lip accuracy; 2) as for the video quality, due to the limited data used to train the renderer, it is vulnerable to out-of-domain input condition and produce bad rendering results occasionally; 3) as for the system efficiency, the slow training and inference speed of the vanilla NeRF severely obstruct its usage in real-world applications. In this paper, we propose GeneFace++ to handle these challenges by 1) utilizing the pitch contour as an auxiliary feature and introducing a temporal loss in the facial motion prediction process; 2) proposing a landmark locally linear embedding method to regulate the outliers in the predicted motion sequence to avoid robustness issues; 3) designing a computationally efficient NeRF-based motion-to-video renderer to achieves fast training and real-time inference. With these settings, GeneFace++ becomes the first NeRF-based method that achieves stable and real-time talking face generation with generalized audio-lip synchronization. Extensive experiments show that our method outperforms state-of-the-art baselines in terms of subjective and objective evaluation. Video samples are available at https://genefaceplusplus.github.io .

Abstract: Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, \emph{etc}. However, most of the existing works have ignored the crucial fact regarding the scarcity of labeled data. With growing internet connectivity to personal life, an enormous amount of documents had been available in the public domain and thus making data annotation a tedious task. We address this challenge using self-supervision and unlike, the few existing self-supervised document segmentation approaches which use text mining and textual labels, we use a complete vision-based approach in pre-training without any ground-truth label or its derivative. Instead, we generate pseudo-layouts from the document images to pre-train an image encoder to learn the document object representation and localization in a self-supervised framework before fine-tuning it with an object detection model. We show that our pipeline sets a new benchmark in this context and performs at par with the existing methods and the supervised counterparts, if not outperforms. The code is made publicly available at: \href{https://github.com/MaitySubhajit/SelfDocSeg}{github.com/MaitySubhajit/SelfDocSeg

Abstract: Facial recognition is one of the most academically studied and industrially developed areas within computer vision where we readily find associated applications deployed globally. This widespread adoption has uncovered significant performance variation across subjects of different racial profiles leading to focused research attention on racial bias within face recognition spanning both current causation and future potential solutions. In support, this study provides an extensive taxonomic review of research on racial bias within face recognition exploring every aspect and stage of the face recognition processing pipeline. Firstly, we discuss the problem definition of racial bias, starting with race definition, grouping strategies, and the societal implications of using race or race-related groupings. Secondly, we divide the common face recognition processing pipeline into four stages: image acquisition, face localisation, face representation, face verification and identification, and review the relevant corresponding literature associated with each stage. The overall aim is to provide comprehensive coverage of the racial bias problem with respect to each and every stage of the face recognition processing pipeline whilst also highlighting the potential pitfalls and limitations of contemporary mitigation strategies that need to be considered within future research endeavours or commercial applications alike.

Abstract: Segment Anything Model (SAM) has attracted significant attention recently, due to its impressive performance on various downstream tasks in a zero-short manner. Computer vision (CV) area might follow the natural language processing (NLP) area to embark on a path from task-specific vision models toward foundation models. However, previous task-specific models are widely recognized as vulnerable to adversarial examples, which fool the model to make wrong predictions with imperceptible perturbation. Such vulnerability to adversarial attacks causes serious concerns when applying deep models to security-sensitive applications. Therefore, it is critical to know whether the vision foundation model SAM can also be easily fooled by adversarial attacks. To the best of our knowledge, our work is the first of its kind to conduct a comprehensive investigation on how to attack SAM with adversarial examples. Specifically, we find that SAM is vulnerable to white-box attacks while maintaining robustness to some extent in the black-box setting. This is an ongoing project and more results and findings will be updated soon through https://github.com/chenshuang-zhang/attack-sam.

Abstract: There has been significant progress in generating an animatable 3D human avatar from a single image. However, recovering texture for the 3D human avatar from a single image has been relatively less addressed. Because the generated 3D human avatar reveals the occluded texture of the given image as it moves, it is critical to synthesize the occluded texture pattern that is unseen from the source image. To generate a plausible texture map for 3D human avatars, the occluded texture pattern needs to be synthesized with respect to the visible texture from the given image. Moreover, the generated texture should align with the surface of the target 3D mesh. In this paper, we propose a texture synthesis method for a 3D human avatar that incorporates geometry information. The proposed method consists of two convolutional networks for the sampling and refining process. The sampler network fills in the occluded regions of the source image and aligns the texture with the surface of the target 3D mesh using the geometry information. The sampled texture is further refined and adjusted by the refiner network. To maintain the clear details in the given image, both sampled and refined texture is blended to produce the final texture map. To effectively guide the sampler network to achieve its goal, we designed a curriculum learning scheme that starts from a simple sampling task and gradually progresses to the task where the alignment needs to be considered. We conducted experiments to show that our method outperforms previous methods qualitatively and quantitatively.

Abstract: Face reenactment methods attempt to restore and re-animate portrait videos as realistically as possible. Existing methods face a dilemma in quality versus controllability: 2D GAN-based methods achieve higher image quality but suffer in fine-grained control of facial attributes compared with 3D counterparts. In this work, we propose StyleAvatar, a real-time photo-realistic portrait avatar reconstruction method using StyleGAN-based networks, which can generate high-fidelity portrait avatars with faithful expression control. We expand the capabilities of StyleGAN by introducing a compositional representation and a sliding window augmentation method, which enable faster convergence and improve translation generalization. Specifically, we divide the portrait scenes into three parts for adaptive adjustments: facial region, non-facial foreground region, and the background. Besides, our network leverages the best of UNet, StyleGAN and time coding for video learning, which enables high-quality video generation. Furthermore, a sliding window augmentation method together with a pre-training strategy are proposed to improve translation generalization and training performance, respectively. The proposed network can converge within two hours while ensuring high image quality and a forward rendering time of only 20 milliseconds. Furthermore, we propose a real-time live system, which further pushes research into applications. Results and experiments demonstrate the superiority of our method in terms of image quality, full portrait video generation, and real-time re-animation compared to existing facial reenactment methods. Training and inference code for this paper are at https://github.com/LizhenWangT/StyleAvatar.

Abstract: Despite the growing adoption of mixed reality and interactive AI agents, it remains challenging for these systems to generate high quality 2D/3D scenes in unseen environments. The common practice requires deploying an AI agent to collect large amounts of data for model training for every new task. This process is costly, or even impossible, for many domains. In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e.g. GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in the physical or virtual world. The heart of our approach is an emerging mechanism, dubbed Augmented Reality with Knowledge Inference Interaction (ArK), which leverages knowledge-memory to generate scenes in unseen physical world and virtual reality environments. The knowledge interactive emergent ability (Figure 1) is demonstrated as the observation learns i) micro-action of cross-modality: in multi-modality models to collect a large amount of relevant knowledge memory data for each interaction task (e.g., unseen scene understanding) from the physical reality; and ii) macro-behavior of reality-agnostic: in mix-reality environments to improve interactions that tailor to different characterized roles, target variables, collaborative information, and so on. We validate the effectiveness of ArK on the scene generation and editing tasks. We show that our ArK approach, combined with large foundation models, significantly improves the quality of generated 2D/3D scenes, compared to baselines, demonstrating the potential benefit of incorporating ArK in generative AI for applications such as metaverse and gaming simulation.