CVPR 2024 Papers

Continual learning can empower vision-language models to continuously acquire new knowledge without the need for access to the entire historical dataset. However mitigating the performance degradation in large-scale models is non-trivial due to (i) parameter shifts throughout lifelong learning and (ii) significant computational burdens associated with full-model tuning. In this work we present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model through the integration of Mixture-of-Experts (MoE) adapters in response to new tasks. To preserve the zero-shot recognition capability of vision-language models we further introduce a Distribution Discriminative Auto-Selector (DDAS) that automatically routes in-distribution and out-of-distribution inputs to the MoE Adapter and the original CLIP respectively. Through extensive experiments across various settings our proposed method consistently outperforms previous state-of-the-art approaches while concurrently reducing parameter training burdens by 60%.

Adversarial examples mislead deep neural networks with imperceptible perturbations and have brought significant threats to deep learning. An important aspect is their transferability which refers to their ability to deceive other models thus enabling attacks in the black-box setting. Though various methods have been proposed to boost transferability the performance still falls short compared with white-box attacks. In this work we observe that existing input transformation based attacks one of the mainstream transfer-based attacks result in different attention heatmaps on various models which might limit the transferability. We also find that breaking the intrinsic relation of the image can disrupt the attention heatmap of the original image. Based on this finding we propose a novel input transformation based attack called block shuffle and rotation (BSR). Specifically BSR splits the input image into several blocks then randomly shuffles and rotates these blocks to construct a set of new images for gradient calculation. Empirical evaluations on the ImageNet dataset demonstrate that BSR could achieve significantly better transferability than the existing input transformation based methods under single-model and ensemble-model settings. Combining BSR with the current input transformation method can further improve the transferability which significantly outperforms the state-of-the-art methods. Code is available at https://github.com/Trustworthy-AI-Group/BSR.

Adversarial training is extensively utilized to improve the adversarial robustness of deep neural networks. Yet mitigating the degradation of standard generalization performance in adversarial-trained models remains an open problem. This paper attempts to resolve this issue through the lens of model complexity. First We leverage the Fisher-Rao norm a geometrically invariant metric for model complexity to establish the non-trivial bounds of the Cross-Entropy Loss-based Rademacher complexity for a ReLU-activated Multi-Layer Perceptron. Building upon this observation we propose a novel regularization framework called Logit-Oriented Adversarial Training (LOAT) which can mitigate the trade-off between robustness and accuracy while imposing only a negligible increase in computational overhead. Our extensive experiments demonstrate that the proposed regularization strategy can boost the performance of the prevalent adversarial training algorithms including PGD-AT TRADES TRADES (LSE) MART and DM-AT across various network architectures. Our code will be available at https://github.com/TrustAI/LOAT.

Accurately predicting the 3D human posture and the pressure exerted on the body for people resting in bed visualized as a body mesh (3D pose & shape) with a 3D pressure map holds significant promise for healthcare applications particularly in the prevention of pressure ulcers. Current methods focus on singular facets of the problem---predicting only 2D/3D poses generating 2D pressure images predicting pressure only for certain body regions instead of the full body or forming indirect approximations to the 3D pressure map. In contrast we introduce BodyMAP which jointly predicts the human body mesh and 3D applied pressure map across the entire human body. Our network leverages multiple visual modalities incorporating both a depth image of a person in bed and its corresponding 2D pressure image acquired from a pressure-sensing mattress. The 3D pressure map is represented as a pressure value at each mesh vertex and thus allows for precise localization of high-pressure regions on the body. Additionally we present BodyMAP-WS a new formulation of pressure prediction in which we implicitly learn pressure in 3D by aligning sensed 2D pressure images with a differentiable 2D projection of the predicted 3D pressure maps. In evaluations with real-world human data our method outperforms the current state-of-the-art technique by 25% on both body mesh and 3D applied pressure map prediction tasks for people in bed.

In visual place recognition accurately identifying and matching images of locations under varying environmental conditions and viewpoints remains a significant challenge. In this paper we introduce a new technique called Bag-of-Queries (BoQ) which learns a set of global queries designed to capture universal place-specific attributes. Unlike existing techniques that employ self-attention and generate the queries directly from the input BoQ employ distinct learnable global queries which probe the input features via cross-attention ensuring consistent information aggregation. In addition this technique provides an interpretable attention mechanism and integrates with both CNN and Vision Transformer backbones. The performance of BoQ is demonstrated through extensive experiments on 14 large-scale benchmarks. It consistently outperforms current state-of-the-art techniques including NetVLAD MixVPR and EigenPlaces. Moreover despite being a global retrieval technique (one-stage) BoQ surpasses two-stage retrieval methods such as Patch-NetVLAD TransVPR and R2Former all while being orders of magnitude faster and more efficient. The code and model weights are publicly available at https://github.com/amaralibey/Bag-of-Queries.

This paper presents an innovative framework designed to train an image deblurring algorithm tailored to a specific camera device. This algorithm works by transforming a blurry input image which is challenging to deblur into another blurry image that is more amenable to deblurring. The transformation process from one blurry state to another leverages unpaired data consisting of sharp and blurry images captured by the target camera device. Learning this blur-to-blur transformation is inherently simpler than direct blur-to-sharp conversion as it primarily involves modifying blur patterns rather than the intricate task of reconstructing fine image details. The efficacy of the proposed approach has been demonstrated through comprehensive experiments on various benchmarks where it significantly outperforms state-of-the-art methods both quantitatively and qualitatively. Our code and data are available at https://github.com/VinAIResearch/Blur2Blur

Video deblurring relies on leveraging information from other frames in the video sequence to restore the blurred regions in the current frame. Mainstream approaches employ bidirectional feature propagation spatio-temporal transformers or a combination of both to extract information from the video sequence. However limitations in memory and computational resources constraints the temporal window length of the spatio-temporal transformer preventing the extraction of longer temporal contextual information from the video sequence. Additionally bidirectional feature propagation is highly sensitive to inaccurate optical flow in blurry frames leading to error accumulation during the propagation process. To address these issues we propose BSSTNet Blur-aware Spatio-temporal Sparse Transformer Network. It introduces the blur map which converts the originally dense attention into a sparse form enabling a more extensive utilization of information throughout the entire video sequence. Specifically BSSTNet (1) uses a longer temporal window in the transformer leveraging information from more distant frames to restore the blurry pixels in the current frame. (2) introduces bidirectional feature propagation guided by blur maps which reduces error accumulation caused by the blur frame. The experimental results demonstrate the proposed BSSTNet outperforms the state-of-the-art methods on the GoPro and DVD datasets.

Graph Convolutional Networks (GCNs) have long set the state-of-the-art in skeleton-based action recognition leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacency matrix. However an inherent flaw has come to light in these cutting-edge models: they tend to optimize the adjacency matrix jointly with the model weights. This process while seemingly efficient causes a gradual decay of bone connectivity data resulting in a model indifferent to the very topology it sought to represent. To remedy this we propose a two-fold strategy: (1) We introduce an innovative approach that encodes bone connectivity by harnessing the power of graph distances to describe the physical topology; we further incorporate action-specific topological representation via persistent homology analysis to depict systemic dynamics. This preserves the vital topological nuances often lost in conventional GCNs. (2) Our investigation also reveals the redundancy in existing GCNs for multi-relational modeling which we address by proposing an efficient refinement to Graph Convolutions (GC) - the BlockGC. This significantly reduces parameters while improving performance beyond original GCNs. Our full model BlockGCN establishes new benchmarks in skeleton-based action recognition across all model categories. Its high accuracy and lightweight design most notably on the large-scale NTU RGB+D 120 dataset stand as strong validation of the efficacy of BlockGCN.

A novel approach to blind image quality assessment called quality comparison network (QCN) is proposed in this paper which sorts the feature vectors of input images according to their quality scores in an embedding space. QCN employs comparison transformers (CTs) and score pivots which act as the centroids of feature vectors of similar-quality images. Each CT updates the score pivots and the feature vectors of input images based on their ordered correlation. To this end we adopt four loss functions. Then we estimate the quality score of a test image by searching the nearest score pivot to its feature vector in the embedding space. Extensive experiments show that the proposed QCN algorithm yields excellent image quality assessment performances on various datasets. Furthermore QCN achieves great performances in cross-dataset evaluation demonstrating its superb generalization capability. The source codes are available at https://github.com/nhshin-mcl/QCN.

Images of the natural world collected by a variety of cameras from drones to individual phones are increasingly abundant sources of biological information. There is an explosion of computational methods and tools particularly computer vision for extracting biologically relevant information from images for science and conservation. Yet most of these are bespoke approaches designed for a specific task and are not easily adaptable or extendable to new questions contexts and datasets. A vision model for general organismal biology questions on images is of timely need. To approach this we curate and release TreeOfLife-10M the largest and most diverse ML-ready dataset of biology images. We then develop BioCLIP a foundation model for the tree of life leveraging the unique properties of biology captured by TreeOfLife-10M namely the abundance and variety of images of plants animals and fungi together with the availability of rich structured biological knowledge. We rigorously benchmark our approach on diverse fine-grained biology classification tasks and find that BioCLIP consistently and substantially outperforms existing baselines (by 17% to 20% absolute). Intrinsic evaluation reveals that BioCLIP has learned a hierarchical representation conforming to the tree of life shedding light on its strong generalizability. All data code and models will be publicly released upon acceptance.

The ability to associate touch with other modalities has huge implications for humans and computational systems. However multimodal learning with touch remains challenging due to the expensive data collection process and non-standardized sensor outputs. We introduce UniTouch a unified tactile model for vision-based touch sensors connected to multiple modalities including vision language and sound. We achieve this by aligning our UniTouch embeddings to pretrained image embeddings already associated with a variety of other modalities. We further propose learnable sensor-specific tokens allowing the model to learn from a set of heterogeneous tactile sensors all at the same time. UniTouch is capable of conducting various touch sensing tasks in the zero-shot setting from robot grasping prediction to touch image question answering. To the best of our knowledge UniTouch is the first to demonstrate such capabilities.

Recently deep neural networks have achieved excellent performance on low-light raw video enhancement. However they often come with high computational complexity and large memory costs which hinder their applications on resource-limited devices. In this paper we explore the feasibility of applying the extremely compact binary neural network (BNN) to low-light raw video enhancement. Nevertheless there are two main issues with binarizing video enhancement models. One is how to fuse the temporal information to improve low-light denoising without complex modules. The other is how to narrow the performance gap between binary convolutions with the full precision ones. To address the first issue we introduce a spatial-temporal shift operation which is easy-to-binarize and effective. The temporal shift efficiently aggregates the features of neighbor frames and the spatial shift handles the misalignment caused by the large motion in videos. For the second issue we present a distribution-aware binary convolution which captures the distribution characteristics of real-valued input and incorporates them into plain binary convolutions to alleviate the degradation in performance. Extensive quantitative and qualitative experiments have shown our high-efficiency binarized low-light raw video enhancement method can attain a promising performance. The code is available at https://github.com/ying-fu/BRVE.

Most existing dynamic or runtime channel pruning methods have to store all weights to achieve efficient inference which brings extra storage costs. Static pruning methods can reduce storage costs directly but their performance is limited by using a fixed sub-network to approximate the original model. Most existing pruning works suffer from these drawbacks because they were designed to only conduct either static or dynamic pruning. In this paper we propose a novel method to solve both efficiency and storage challenges via simultaneously conducting dynamic and static channel pruning for convolutional neural networks. We propose a new bi-level optimization based model to naturally integrate the static and dynamic channel pruning. By doing so our method enjoys benefits from both sides and the disadvantages of dynamic and static pruning are reduced. After pruning we permanently remove redundant parameters and then finetune the model with dynamic flexibility. Experimental results on CIFAR-10 and ImageNet datasets suggest that our method can achieve state-of-the-art performance compared to existing dynamic and static channel pruning methods.

Depth completion aims to derive a dense depth map from sparse depth measurements with a synchronized color image. Current state-of-the-art (SOTA) methods are predominantly propagation-based which work as an iterative refinement on the initial estimated dense depth. However the initial depth estimations mostly result from direct applications of convolutional layers on the sparse depth map. In this paper we present a Bilateral Propagation Network (BP-Net) that propagates depth at the earliest stage to avoid directly convolving on sparse data. Specifically our approach propagates the target depth from nearby depth measurements via a non-linear model whose coefficients are generated through a multi-layer perceptron conditioned on both radiometric difference and spatial distance. By integrating bilateral propagation with multi-modal fusion and depth refinement in a multi-scale framework our BP-Net demonstrates outstanding performance on both indoor and outdoor scenes. It achieves SOTA on the NYUv2 dataset and ranks 1st on the KITTI depth completion benchmark at the time of submission. Experimental results not only show the effectiveness of bilateral propagation but also emphasize the significance of early-stage propagation in contrast to the refinement stage. Our code and trained models will be available on the project page.

Event Stream Super-Resolution (ESR) aims to address the challenge of insufficient spatial resolution in event streams which holds great significance for the application of event cameras in complex scenarios. Previous works for ESR often process positive and negative events in a mixed paradigm. This paradigm limits their ability to effectively model the unique characteristics of each event and mutually refine each other by considering their correlations. In this paper we propose a bilateral event mining and complementary network (BMCNet) to fully leverage the potential of each event and capture the shared information to complement each other simultaneously. Specifically we resort to a two-stream network to accomplish comprehensive mining of each type of events individually. To facilitate the exchange of information between two streams we propose a bilateral information exchange (BIE) module. This module is layer-wisely embedded between two streams enabling the effective propagation of hierarchical global information while alleviating the impact of invalid information brought by inherent characteristics of events. The experimental results demonstrate that our approach outperforms the previous state-of-the-art methods in ESR achieving performance improvements of over 11% on both real and synthetic datasets. Moreover our method significantly enhances the performance of event-based downstream tasks such as object recognition and video reconstruction. Our code is available at https://github.com/Lqm26/BMCNet-ESR.

Human-Object Interaction (HOI) Detection constitutes an important aspect of human-centric scene understanding which requires precise object detection and interaction recognition. Despite increasing advancement in detection recognizing subtle and intricate interactions remains challenging. Recent methods have endeavored to leverage the rich semantic representation from pre-trained CLIP yet fail to efficiently capture finer-grained spatial features that are highly informative for interaction discrimination. In this work instead of solely using representations from CLIP we fill the gap by proposing a spatial adapter that efficiently utilizes the multi-scale spatial information in the pre-trained detector. This leads to a bilateral adaptation that mutually produces complementary features. To further improve interaction recognition under occlusion which is common in crowded scenarios we propose an Occluded Part Extrapolation module that guides the model to recover the spatial details from manually occluded feature maps. Moreover we design a Conditional Contextual Mining module that further mines informative contextual clues from the spatial features via a tailored cross-attention mechanism. Extensive experiments on V-COCO and HICO-DET benchmarks demonstrate that our method significantly outperforms prior art on both standard and zero-shot settings resulting in new state-of-the-art performance. Additional ablation studies further validate the effectiveness of each component in our method.

Gait recognition stands as one of the most pivotal remote identification technologies and progressively expands across research and industry communities. However existing gait recognition methods heavily rely on task-specific upstream driven by supervised learning to provide explicit gait representations like silhouette sequences which inevitably introduce expensive annotation costs and potential error accumulation. Escaping from this trend this work explores effective gait representations based on the all-purpose knowledge produced by task-agnostic Large Vision Models (LVMs) and proposes a simple yet efficient gait framework termed BigGait. Specifically the Gait Representation Extractor (GRE) within BigGait draws upon design principles from established gait representations effectively transforming all-purpose knowledge into implicit gait representations without requiring third-party supervision signals. Experiments on CCPG CAISA-B* and SUSTech1K indicate that BigGait significantly outperforms the previous methods in both within-domain and cross-domain tasks in most cases and provides a more practical paradigm for learning the next-generation gait representation. Finally we delve into prospective challenges and promising directions in LVMs-based gait recognition aiming to inspire future work in this emerging topic. The source code is available at https://github.com/ShiqiYu/OpenGait.

How to effectively explore multi-scale representations of rain streaks is important for image deraining. In contrast to existing Transformer-based methods that depend mostly on single-scale rain appearance we develop an end-to-end multi-scale Transformer that leverages the potentially useful features in various scales to facilitate high-quality image reconstruction. To better explore the common degradation representations from spatially-varying rain streaks we incorporate intra-scale implicit neural representations based on pixel coordinates with the degraded inputs in a closed-loop design enabling the learned features to facilitate rain removal and improve the robustness of the model in complex scenarios. To ensure richer collaborative representation from different scales we embed a simple yet effective inter-scale bidirectional feedback operation into our multi-scale Transformer by performing coarse-to-fine and fine-to-coarse information communication. Extensive experiments demonstrate that our approach named as NeRD-Rain performs favorably against the state-of-the-art ones on both synthetic and real-world benchmark datasets. The source code and trained models are available at https://github.com/cschenxiang/NeRD-Rain.

Dance serves as a powerful medium for expressing human emotions but the lifelike generation of dance is still a considerable challenge. Recently diffusion models have showcased remarkable generative abilities across various domains. They hold promise for human motion generation due to their adaptable many-to-many nature. Nonetheless current diffusion-based motion generation models often create entire motion sequences directly and unidirectionally lacking focus on the motion with local and bidirectional enhancement. When choreographing high-quality dance movements people need to take into account not only the musical context but also the nearby music-aligned dance motions. To authentically capture human behavior we propose a Bidirectional Autoregressive Diffusion Model (BADM) for music-to-dance generation where a bidirectional encoder is built to enforce that the generated dance is harmonious in both the forward and backward directions. To make the generated dance motion smoother a local information decoder is built for local motion enhancement. The proposed framework is able to generate new motions based on the input conditions and nearby motions which foresees individual motion slices iteratively and consolidates all predictions. To further refine the synchronicity between the generated dance and the beat the beat information is incorporated as an input to generate better music-aligned dance movements. Experimental results demonstrate that the proposed model achieves state-of-the-art performance compared to existing unidirectional approaches on the prominent benchmark for music-to-dance generation.