CVPR 2024 论文列表

Deep-learning-based gaze estimation approaches often suffer from notable performance degradation in unseen target domains. One of the primary reasons is that the Fully Connected layer is highly prone to overfitting when mapping the high-dimensional image feature to 3D gaze. In this paper we propose Analytical Gaze Generalization framework (AGG) to improve the generalization ability of gaze estimation models without touching target domain data. The AGG consists of two modules the Geodesic Projection Module (GPM) and the Sphere-Oriented Training (SOT). GPM is a generalizable replacement of FC layer which projects high-dimensional image features to 3D space analytically to extract the principle components of gaze. Then we propose Sphere-Oriented Training (SOT) to incorporate the GPM into the training process and further improve cross-domain performances. Experimental results demonstrate that the AGG effectively alleviate the overfitting problem and consistently improves the cross-domain gaze estimation accuracy in 12 cross-domain settings without requiring any target domain data. The insight from the Analytical Gaze Generalization framework has the potential to benefit other regression tasks with physical meanings.

In the realm of computer vision Neural Fields have gained prominence as a contemporary tool harnessing neural networks for signal representation. Despite the remarkable progress in adapting these networks to solve a variety of problems the field still lacks a comprehensive theoretical framework. This article aims to address this gap by delving into the intricate interplay between initialization and activation providing a foundational basis for the robust optimization of Neural Fields. Our theoretical insights reveal a deep-seated connection among network initialization architectural choices and the optimization process emphasizing the need for a holistic approach when designing cutting-edge Neural Fields.

Video deblurring aims to restore sharp frames from blurred video clips. Despite notable progress in video deblurring works it is still a challenging problem because of the loss of motion information during the duration of the exposure time. Since event cameras can capture clear motion information asynchronously with high temporal resolution several works exploit the event camera for deblurring as they can provide abundant motion information. However despite these approaches there were few cases of actively exploiting the long-range temporal dependency of videos. To tackle these deficiencies we present an event-based video deblurring framework by actively utilizing temporal information from videos. To be specific we first introduce a frequency-based cross-modal feature enhancement module. Second we propose event-guided video alignment modules by considering the valuable characteristics of the event and videos. In addition we designed a hybrid camera system to collect the first real-world event-based video deblurring dataset. For the first time we build a dataset containing synchronized high-resolution real-world blurred videos and corresponding sharp videos and event streams. Experimental results validate that our frameworks significantly outperform the state-of-the-art frame-based and event-based deblurring works in the various datasets. In addition we designed a hybrid camera system to collect the first real-world event-based video deblurring dataset. For the first time we build a dataset containing synchronized high-resolution real-world blurred videos and corresponding sharp videos and event streams. Experimental results validate that our frameworks significantly outperform the state-of-the-art frame-based and event-based deblurring works in the various datasets. The project pages are available at https://sites.google.com/view/fevd-cvpr2024.

To serve the intricate and varied demands of image editing precise and flexible manipulation in image content is indispensable. Recently Drag-based editing methods have gained impressive performance. However these methods predominantly center on point dragging resulting in two noteworthy drawbacks namely "miss tracking" where difficulties arise in accurately tracking the predetermined handle points and "ambiguous tracking" where tracked points are potentially positioned in wrong regions that closely resemble the handle points. To address the above issues we propose FreeDrag a feature dragging methodology designed to free the burden on point tracking. The FreeDrag incorporates two key designs i.e. template feature via adaptive updating and line search with backtracking the former improves the stability against drastic content change by elaborately controlling the feature updating scale after each dragging while the latter alleviates the misguidance from similar points by actively restricting the search area in a line. These two technologies together contribute to a more stable semantic dragging with higher efficiency. Comprehensive experimental results substantiate that our approach significantly outperforms pre-existing methodologies offering reliable point-based editing even in various complex scenarios.

Benefiting from large-scale pre-trained text-to-image (T2I) generative models impressive progress has been achieved in customized image generation which aims to generate user-specified concepts. Existing approaches have extensively focused on single-concept customization and still encounter challenges when it comes to complex scenarios that involve combining multiple concepts. These approaches often require retraining/fine-tuning using a few images leading to time-consuming training processes and impeding their swift implementation. Furthermore the reliance on multiple images to represent a singular concept increases the difficulty of customization. To this end we propose FreeCustom a novel tuning-free method to generate customized images of multi-concept composition based on reference concepts using only one image per concept as input. Specifically we introduce a new multi-reference self-attention (MRSA) mechanism and a weighted mask strategy that enables the generated image to access and focus more on the reference concepts. In addition MRSA leverages our key finding that input concepts are better preserved when providing images with context interactions. Experiments show that our method's produced images are consistent with the given concepts and better aligned with the input text. Our method outperforms or performs on par with other training-based methods in terms of multi-concept composition and single-concept customization but is simpler. Codes can be found \href https://github.com/aim-uofa/FreeCustom here .

In this paper we study the problem of generalizable synthetic image detection aiming to detect forgery images from diverse generative methods e.g. GANs and diffusion models. Cutting-edge solutions start to explore the benefits of pre-trained models and mainly follow the fixed paradigm of solely training an attached classifier e.g. combining frozen CLIP-ViT with a learnable linear layer in UniFD. However our analysis shows that such a fixed paradigm is prone to yield detectors with insufficient learning regarding forgery representations. We attribute the key challenge to the lack of forgery adaptation and present a novel forgery-aware adaptive transformer approach namely FatFormer. Based on the pre-trained vision-language spaces of CLIP FatFormer introduces two core designs for the adaption to build generalized forgery representations. First motivated by the fact that both image and frequency analysis are essential for synthetic image detection we develop a forgery-aware adapter to adapt image features to discern and integrate local forgery traces within image and frequency domains. Second we find that considering the contrastive objectives between adapted image features and text prompt embeddings a previously overlooked aspect results in a nontrivial generalization improvement. Accordingly we introduce language-guided alignment to supervise the forgery adaptation with image and text prompts in FatFormer. Experiments show that by coupling these two designs our approach tuned on 4-class ProGAN data attains a remarkable detection performance achieving an average of 98% accuracy to unseen GANs and surprisingly generalizes to unseen diffusion models with 95% accuracy.

We introduce Florence-2 a novel vision foundation model with a unified prompt-based representation for various computer vision and vision-language tasks. While existing large vision models excel in transfer learning they struggle to perform diverse tasks with simple instructions a capability that implies handling the complexity of various spatial hierarchy and semantic granularity. Florence-2 was designed to take text-prompt as task instructions and generate desirable results in text forms whether it be captioning object detection grounding or segmentation. This multi-task learning setup demands large-scale high-quality annotated data. To this end we co-developed FLD-5B that consists of 5.4 billion comprehensive visual annotations on 126 million images using an iterative strategy of automated image annotation and model refinement. We adopted a sequence-to-sequence structure to train Florence-2 to perform versatile and comprehensive vision tasks. Extensive evaluations on numerous tasks demonstrated Florence-2 to be a strong vision foundation model contender with unprecedented zero-shot and fine-tuning capabilities.

While recent depth completion methods have achieved remarkable results filling in relatively dense depth maps (e.g. projected 64-line LiDAR on KITTI or 500 sampled points on NYUv2) with RGB guidance their performance on very sparse input (e.g. 4-line LiDAR or 32 depth point measurements) is unverified. These sparser regimes present new challenges as a 4-line LiDAR increases the distance between pixels without depth and their nearest depth point sixfold from 5 pixels to 30 pixels compared to 64 lines. Observing that existing methods struggle with sparse and variable distribution depth maps we propose an Affinity-Based Shift Correction (ASC) module that iteratively aligns depth predictions to input depth based on predicted affinities between image pixels and depth points. Our framework enables each depth point to adaptively influence and improve predictions across the image leading to largely improved results for fewer-line fewer-point and variable sparsity settings. Further we show improved performance in domain transfer from KITTI to nuScenes and from random sampling to irregular point distributions. Our correction module can easily be added to any depth completion or RGB-only depth estimation model notably allowing the latter to perform both completion and estimation with a single model.

Periocular and face are complementary biometrics for identity management albeit with inherent limitations notably in scenarios involving occlusion due to sunglasses or masks. In response to these challenges we introduce Flexible Biometric Recognition (FBR) a novel framework designed to advance conventional face periocular and multimodal face-periocular biometrics across both intra- and cross-modality recognition tasks. FBR strategically utilizes the Multimodal Fusion Attention (MFA) and Multimodal Prompt Tuning (MPT) mechanisms within the Vision Transformer architecture. MFA facilitates the fusion of modalities ensuring cohesive alignment between facial and periocular embeddings while incorporating soft-biometrics to enhance the model's ability to discriminate between individuals. The fusion of three modalities is pivotal in exploring interrelationships between different modalities. Additionally MPT serves as a unifying bridge intertwining inputs and promoting cross-modality interactions while preserving their distinctive characteristics. The collaborative synergy of MFA and MPT enhances the shared features of the face and periocular with a specific emphasis on the ocular region yielding exceptional performance in both intra- and cross-modality recognition tasks. Rigorous experimentation across four benchmark datasets validates the noteworthy performance of the FBR model. The source code is available at https://github.com/MIS-DevWorks/FBR.

Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on this framework and propose a new pruning at initialization algorithm that leverages the Neural Tangent Kernel (NTK) theory to align the training dynamics of the sparse network with that of the dense one. Specifically we show how the usually neglected data-dependent component in the NTK's spectrum can be taken into account by providing an analytical upper bound to the NTK's trace obtained by decomposing neural networks into individual paths. This leads to our Path eXclusion (PX) a foresight pruning method designed to preserve the parameters that mostly influence the NTK's trace. PX is able to find lottery tickets (i.e. good paths) even at high sparsity levels and largely reduces the need for additional training. When applied to pre-trained models it extracts subnetworks directly usable for several downstream tasks resulting in performance comparable to those of the dense counterpart but with substantial cost and computational savings.

Federated learning is a promising framework to train neural networks with widely distributed data. However performance degrades heavily with heterogeneously distributed data. Recent work has shown this is due to the final layer of the network being most prone to local bias some finding success freezing the final layer as an orthogonal classifier. We investigate the training dynamics of the classifier by applying SVD to the weights motivated by the observation that freezing weights results in constant singular values. We find that there are differences when training in IID and non-IID settings. Based on this finding we introduce two regularization terms for local training to continuously emulate IID settings: (1) variance in the dimension-wise probability distribution of the classifier and (2) hyperspherical uniformity of representations of the encoder. These regularizations promote local models to act as if it were in an IID setting regardless of the local data distribution thus offsetting proneness to bias while being flexible to the data. On extensive experiments in both label-shift and feature-shift settings we verify that our method achieves highest performance by a large margin especially in highly non-IID cases in addition to being scalable to larger models and datasets.

Recent dataset deduplication techniques have demonstrated that content-aware dataset pruning can dramatically reduce the cost of training Vision-Language Pretrained (VLP) models without significant performance losses compared to training on the original dataset. These results have been based on pruning commonly used image-caption datasets collected from the web -- datasets that are known to harbor harmful social biases that may then be codified in trained models. In this work we evaluate how deduplication affects the prevalence of these biases in the resulting trained models and introduce an easy-to-implement modification to the recent SemDeDup algorithm that can reduce the negative effects that we observe. When examining CLIP-style models trained on deduplicated variants of LAION-400M we find our proposed FairDeDup algorithm consistently leads to improved fairness metrics over SemDeDup on the FairFace and FACET datasets while maintaining zero-shot performance on CLIP benchmarks.

Fairness is a critical concern in deep learning especially in healthcare where these models influence diagnoses and treatment decisions. Although fairness has been investigated in the vision-only domain the fairness of medical vision-language (VL) models remains unexplored due to the scarcity of medical VL datasets for studying fairness. To bridge this research gap we introduce the first fair vision-language medical dataset (Harvard-FairVLMed) that provides detailed demographic attributes ground-truth labels and clinical notes to facilitate an in-depth examination of fairness within VL foundation models. Using Harvard-FairVLMed we conduct a comprehensive fairness analysis of two widely-used VL models (CLIP and BLIP2) pre-trained on both natural and medical domains across four different protected attributes. Our results highlight significant biases in all VL models with Asian Male Non-Hispanic and Spanish being the preferred subgroups across the protected attributes of race gender ethnicity and language respectively. In order to alleviate these biases we propose FairCLIP an optimal-transport-based approach that achieves a favorable trade-off between performance and fairness by reducing the Sinkhorn distance between the overall sample distribution and the distributions corresponding to each demographic group. As the first VL dataset of its kind Harvard-FairVLMed holds the potential to catalyze advancements in the development of machine learning models that are both ethically aware and clinically effective. Our dataset and code are available at https://ophai.hms.harvard.edu/datasets/harvard-fairvlmed10k.

Despite the remarkable success of Vision Transformers (ViT) across diverse fields in computer vision they have a clear drawback of expensive adaption cost for downstream tasks due to the increased scale. To address this Visual Prompt Tuning (VPT) incorporates learnable parameters in the input space of ViT. While freezing the ViT backbone and tuning only the prompts it exhibits superior performances to full fine-tuning. However despite the outstanding advantage we point out that VPT may lead to serious unfairness in downstream classification. Initially we investigate the causes of unfairness in VPT identifying the biasedly pre-trained ViT as a principal factor. Motivated by this observation we propose a Fair Visual Prompt Tuning (Fair-VPT) which removes biased information in the pre-trained ViT while adapting it to downstream classification tasks. To this end we categorize prompts into "cleaner prompts" and "target prompts". Based on this we encode the class token in two different ways by either masking or not masking the target prompts in the self-attention process. These encoded tokens are trained with distinct objective functions resulting in the inclusion of different information in the target and cleaner prompts. Moreover we introduce a disentanglement loss based on contrastive learning to further decorrelate them. In experiments across diverse benchmarks the proposed method demonstrates the most superior performance in terms of balanced classification accuracy and fairness.

The task of face reenactment is to transfer the head motion and facial expressions from a driving video to the appearance of a source image which may be of a different person (cross-reenactment). Most existing methods are CNN-based and estimate optical flow from the source image to the current driving frame which is then inpainted and refined to produce the output animation. We propose a transformer-based encoder for computing a set-latent representation of the source image(s). We then predict the output color of a query pixel using a transformer-based decoder which is conditioned with keypoints and a facial expression vector extracted from the driving frame. Latent representations of the source person are learned in a self-supervised manner that factorize their appearance head pose and facial expressions. Thus they are perfectly suited for cross-reenactment. In contrast to most related work our method naturally extends to multiple source images and can thus adapt to person-specific facial dynamics. We also propose data augmentation and regularization schemes that are necessary to prevent overfitting and support generalizability of the learned representations. We evaluated our approach in a randomized user study. The results indicate superior performance compared to the state-of-the-art in terms of motion transfer quality and temporal consistency.

We present a joint learning scheme of video super-resolution and deblurring called VSRDB to restore clean high-resolution (HR) videos from blurry low-resolution (LR) ones. This joint restoration problem has drawn much less attention compared to single restoration problems. In this paper we propose a novel flow-guided dynamic filtering (FGDF) and iterative feature refinement with multi-attention (FRMA) which constitutes our VSRDB framework denoted as FMA-Net. Specifically our proposed FGDF enables precise estimation of both spatio-temporally-variant degradation and restoration kernels that are aware of motion trajectories through sophisticated motion representation learning. Compared to conventional dynamic filtering the FGDF enables the FMA-Net to effectively handle large motions into the VSRDB. Additionally the stacked FRMA blocks trained with our novel temporal anchor (TA) loss which temporally anchors and sharpens features refine features in a coarse-to-fine manner through iterative updates. Extensive experiments demonstrate the superiority of the proposed FMA-Net over state-of-the-art methods in terms of both quantitative and qualitative quality. Codes and pre-trained models are available at: https://kaist-viclab.github.io/fmanet-site.

Despite noise and caption quality having been acknowledged as important factors impacting vision-language contrastive pre-training in this paper we show that the full potential of improving the training process by addressing such issues is yet to be realized. Specifically we firstly study and analyze two issues affecting training: incorrect assignment of negative pairs and low caption quality and diversity. Then we devise effective solutions for addressing both problems which essentially require training with multiple true positive pairs. Finally we propose training with sigmoid loss to address such a requirement. We show very large gains over the current state-of-the-art for both image recognition ( +6% on average over 11 datasets) and image retrieval ( +19% on Flickr30k and +15% on MSCOCO).

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However the visual component typically depends only on the instance-level contrastive language-image pre-training (CLIP). Our research reveals that the visual capabilities in recent MultiModal LLMs (MLLMs) still exhibit systematic shortcomings. To understand the roots of these errors we explore the gap between the visual embedding space of CLIP and vision-only self-supervised learning. We identify "CLIP-blind pairs" - images that CLIP perceives as similar despite their clear visual differences. With these pairs we construct the Multimodal Visual Patterns (MMVP) benchmark. MMVP exposes areas where state-of-the-art systems including GPT-4V struggle with straightforward questions across nine basic visual patterns often providing incorrect answers and hallucinated explanations. We further evaluate various CLIP-based vision-and-language models and found a notable correlation between visual patterns that challenge CLIP models and those problematic for multimodal LLMs. As an initial effort to address these issues we propose a Mixture of Features (MoF) approach demonstrating that integrating vision self-supervised learning features with MLLMs can significantly enhance their visual grounding capabilities. Together our research suggests visual representation learning remains an open challenge and accurate visual grounding is crucial for future successful multimodal systems.

Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities their performance is still inferior to specialized models on downstream tasks which makes adaptation necessary to enhance their utility. However fine-tuning methods require independent training for every model leading to huge computation and memory overheads. In this paper we propose a novel setting where we aim to improve the performance of diverse MLLMs with a group of shared parameters optimized for a downstream task. To achieve this we propose Transferable Visual Prompting (TVP) a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts including 1) Feature Consistency Alignment: which imposes constraints to the prompted feature changes to maintain task-agnostic knowledge; 2) Task Semantics Enrichment: which encourages the prompted images to contain richer task-specific semantics with language guidance. We validate the effectiveness of TVP through extensive experiments with 6 modern MLLMs on a wide variety of tasks ranging from object recognition and counting to multimodal reasoning and hallucination correction.