CVPR 2024 论文列表

Standard federated learning approaches suffer when client data distributions have sufficient heterogeneity. Recent methods addressed the client data heterogeneity issue via personalized federated learning (PFL) - a class of FL algorithms aiming to personalize learned global knowledge to better suit the clients' local data distributions. Existing PFL methods usually decouple global updates in deep neural networks by performing personalization on particular layers (i.e. classifier heads) and global aggregation for the rest of the network. However preselecting network layers for personalization may result in suboptimal storage of global knowledge. In this work we propose FedSelect a novel PFL algorithm inspired by the iterative subnetwork discovery procedure used for the Lottery Ticket Hypothesis. FedSelect incrementally expands subnetworks to personalize client parameters concurrently conducting global aggregations on the remaining parameters. This approach enables the personalization of both client parameters and subnetwork structure during the training process. Finally we show that FedSelect outperforms recent state-of-the-art PFL algorithms under challenging client data heterogeneity settings and demonstrates robustness to various real-world distributional shifts.

Federated Learning (FL) aggregates locally trained models from individual clients to construct a global model. While FL enables learning a model with data privacy it often suffers from significant performance degradation when clients have heterogeneous data distributions. This data heterogeneity causes the model to forget the global knowledge acquired from previously sampled clients after being trained on local datasets. Although the introduction of proximal objectives in local updates helps to preserve global knowledge it can also hinder local learning by interfering with local objectives. Inspired by Continual Learning (CL) we adopt an orthogonal learning strategy to balance these two conflicting objectives. However we observe that directly negating the proximal gradient in the local gradient significantly undermines local learning. To address the problem we propose a novel method Federated Stabilized Orthogonal Learning (FedSOL). FedSOL is designed to identify gradients of local objectives that are inherently orthogonal to directions affecting the proximal objective. Specifically FedSOL targets parameter regions where learning on the local objective is minimally influenced by proximal weight perturbations. Our experiments demonstrate that FedSOL consistently achieves state-of-the-art performance across various scenarios.

Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However its application on resource-constrained devices is challenging due to the high demand for computation and memory resources to train deep learning models. Neural network pruning techniques such as dynamic pruning could enhance model efficiency but directly adopting them in FL still poses substantial challenges including post-pruning performance degradation high activation memory usage etc. To address these challenges we propose FedMef a novel and memory-efficient federated dynamic pruning framework. FedMef comprises two key components. First we introduce the budget-aware extrusion that maintains pruning efficiency while preserving post-pruning performance by salvaging crucial information from parameters marked for pruning within a given budget. Second we propose scaled activation pruning to effectively reduce activation memory footprints which is particularly beneficial for deploying FL to memory-limited devices. Extensive experiments demonstrate the effectiveness of our proposed FedMef. In particular it achieves a significant reduction of 28.5% in memory footprint compared to state-of-the-art methods while obtaining superior accuracy.

Federated Learning (FL) enables joint training across distributed clients using their local data privately. Federated Multi-Task Learning (FMTL) builds on FL to handle multiple tasks assuming model congruity that identical model architecture is deployed in each client. To relax this assumption and thus extend real-world applicability we introduce a novel problem setting Hetero-Client Federated Multi-Task Learning (HC-FMTL) to accommodate diverse task setups. The main challenge of HC-FMTL is the model incongruity issue that invalidates conventional aggregation methods. It also escalates the difficulties in model aggregation to deal with data and task heterogeneity inherent in FMTL. To address these challenges we propose the FedHCA^2 framework which allows for federated training of personalized models by modeling relationships among heterogeneous clients. Drawing on our theoretical insights into the difference between multi-task and federated optimization we propose the Hyper Conflict-Averse Aggregation scheme to mitigate conflicts during encoder updates. Additionally inspired by task interaction in MTL the Hyper Cross Attention Aggregation scheme uses layer-wise cross attention to enhance decoder interactions while alleviating model incongruity. Moreover we employ learnable Hyper Aggregation Weights for each client to customize personalized parameter updates. Extensive experiments demonstrate the superior performance of FedHCA^2 in various HC-FMTL scenarios compared to representative methods. Code is available at https://github.com/innovator-zero/FedHCA2.

Personalized Federated Learning (PFL) is primarily designed to provide customized models for each client to better fit the non-iid distributed client data which is a inherent challenge in Federated Learning. However current PFL methods suffer from inconsistencies in both intra-client and inter-client levels: 1) The intra-client inconsistency stems from the asynchronous update strategy for personalized and shared parameters. In PFL clients update their shared parameters to communicate and learn from others while keeping personalized parts unchanged leading to poor coordination between these two components. 2) The Inter-client inconsistency arises from "stragglers" - inactive clients that communicate and train with the server less frequently. This results in their under-trained personalized models and impedes the collaborative training stage for other clients. In this paper we present a novel PFL framework named FedAS which uses Federated Parameter-Alignment and Client-Synchronization to overcome above challenges. Initially we enhance the localization of global parameters by infusing them with local insights. We make the shared parts learn from previous model thereby increasing their local relevance and reducing the impact of parameter inconsistency. Furthermore we design a robust aggregation method to mitigate the impact of stragglers by preventing the incorporation of their under-trained knowledge into aggregated model. Experimental results on Cifar10 and Cifar100 validate the effectiveness of our FedAS in achieving better performance and robustness against data heterogeneity.

Multiple instance learning (MIL) is the most widely used framework in computational pathology encompassing sub-typing diagnosis prognosis and more. However the existing MIL paradigm typically requires an offline instance feature extractor such as a pre-trained ResNet or a foundation model. This approach lacks the capability for feature fine-tuning within the specific downstream tasks limiting its adaptability and performance. To address this issue we propose a Re-embedded Regional Transformer (RRT) for re-embedding the instance features online which captures fine-grained local features and establishes connections across different regions. Unlike existing works that focus on pre-training powerful feature extractor or designing sophisticated instance aggregator RRT is tailored to re-embed instance features online. It serves as a portable module that can seamlessly integrate into mainstream MIL models. Extensive experimental results on common computational pathology tasks validate that: 1) feature re-embedding improves the performance of MIL models based on ResNet-50 features to the level of foundation model features and further enhances the performance of foundation model features; 2) the RRT can introduce more significant performance improvements to various MIL models; 3) RRT-MIL as an RRT-enhanced AB-MIL outperforms other latest methods by a large margin. The code is available at: https://github.com/DearCaat/RRT-MIL.

3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times some work has emerged that aims to extend the functionality of NeRF beyond view synthesis for semantically aware tasks such as editing and segmentation using 3D feature field distillation from 2D foundation models. However these methods have two major limitations: (a) they are limited by the rendering speed of NeRF pipelines and (b) implicitly represented feature fields suffer from continuity artifacts reducing feature quality. Recently 3D Gaussian Splatting has shown state-of-the-art performance on real-time radiance field rendering. In this work we go one step further: in addition to radiance field rendering we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation. This translation is not straightforward: naively incorporating feature fields in the 3DGS framework encounters significant challenges notably the disparities in spatial resolution and channel consistency between RGB images and feature maps. We propose architectural and training changes to efficiently avert this problem. Our proposed method is general and our experiments showcase novel view semantic segmentation language-guided editing and segment anything through learning feature fields from state-of-the-art 2D foundation models such as SAM and CLIP-LSeg. Across experiments our distillation method is able to provide comparable or better results while being significantly faster to both train and render. Additionally to the best of our knowledge we are the first method to enable point and bounding-box prompting for radiance field manipulation by leveraging the SAM model. Project website at: https://feature-3dgs.github.io/

3D correspondence i.e. a pair of 3D points is a fundamental concept in computer vision. A set of 3D correspondences when equipped with compatibility edges forms a correspondence graph. This graph is a critical component in several state-of-the-art 3D point cloud registration approaches e.g. the one based on maximal cliques (MAC). However its properties have not been well understood. So we present the first study that introduces graph signal processing into the domain of correspondence graph. We exploit the generalized degree signal on correspondence graph and pursue sampling strategies that preserve high-frequency components of this signal. To address time-consuming singular value decomposition in deterministic sampling we resort to a stochastic approximate sampling strategy. As such the core of our method is the stochastic spectral sampling of correspondence graph. As an application we build a complete 3D registration algorithm termed as FastMAC that reaches real-time speed while leading to little to none performance drop. Through extensive experiments we validate that FastMAC works for both indoor and outdoor benchmarks. For example FastMAC can accelerate MAC by 80 times while maintaining high registration success rate on KITTI. Codes are publicly available at https://github.com/Forrest-110/FastMAC.

Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs) with the aim of obtaining an accurate solution with as few number of function evaluations (NFE) as possible. Recently various fast samplers utilizing higher-order ODE solvers have emerged and achieved better performance than the initial first-order one. However these numerical methods inherently result in certain approximation errors which significantly degrades sample quality with extremely small NFE (e.g. around 5). In contrast based on the geometric observation that each sampling trajectory almost lies in a two-dimensional subspace embedded in the ambient space we propose Approximate MEan-Direction Solver (AMED-Solver) that eliminates truncation errors by directly learning the mean direction for fast diffusion sampling. Besides our method can be easily used as a plugin to further improve existing ODE-based samplers. Extensive experiments on image synthesis with the resolution ranging from 32 to 512 demonstrate the effectiveness of our method. With only 5 NFE we achieve 6.61 FID on CIFAR-10 10.74 FID on ImageNet 64x64 and 13.20 FID on LSUN Bedroom. Our code is available at https://github.com/zju-pi/diff-sampler.

Domain shift is a challenge for supervised human pose estimation where the source data and target data come from different distributions. This is why pose estimation methods generally perform worse on the test set than on the training set. Recently test-time adaptation has proven to be an effective way to deal with domain shift in human pose estimation. Although the performance on the target domain has been improved existing methods require a large number of weight updates for convergence which is time-consuming and brings catastrophic forgetting. To solve these issues we propose a meta-auxiliary learning method to achieve fast adaptation for domain shift during inference. Specifically we take human pose estimation as the supervised primary task and propose body-specific image inpainting as a self-supervised auxiliary task. First we jointly train the primary and auxiliary tasks to get a pre-trained model on the source domain. Then meta-training correlates the performance of the two tasks to learn a good weight initialization. Finally meta-testing adapts the meta-learned model to the target data through self-supervised learning. Benefiting from the meta-learning paradigm the proposed method enables fast adaptation to the target domain while preserving the source domain knowledge. The carefully designed auxiliary task better pays attention to human-related semantics in a single image. Extensive experiments demonstrate the effectiveness of our test-time fast adaptation.

As an important pillar of underwater intelligence Marine Animal Segmentation (MAS) involves segmenting animals within marine environments. Previous methods don't excel in extracting long-range contextual features and overlook the connectivity between discrete pixels. Recently Segment Anything Model (SAM) offers a universal framework for general segmentation tasks. Unfortunately trained with natural images SAM does not obtain the prior knowledge from marine images. In addition the single-position prompt of SAM is very insufficient for prior guidance. To address these issues we propose a novel feature learning framework named Dual-SAM for high-performance MAS. To this end we first introduce a dual structure with SAM's paradigm to enhance feature learning of marine images. Then we propose a Multi-level Coupled Prompt (MCP) strategy to instruct comprehensive underwater prior information and enhance the multi-level features of SAM's encoder with adapters. Subsequently we design a Dilated Fusion Attention Module (DFAM) to progressively integrate multi-level features from SAM's encoder. Finally instead of directly predicting the masks of marine animals we propose a Criss-Cross Connectivity Prediction (C3P) paradigm to capture the inter-connectivity between discrete pixels. With dual decoders it generates pseudo-labels and achieves mutual supervision for complementary feature representations resulting in considerable improvements over previous techniques. Extensive experiments verify that our proposed method achieves state-of-the-art performances on five widely-used MAS datasets. The code is available at https://github.com/Drchip61/Dual SAM.

Due to the high potential for abuse of GenAI systems the task of detecting synthetic images has recently become of great interest to the research community. Unfortunately existing image space detectors quickly become obsolete as new high-fidelity text-to-image models are developed at blinding speed. In this work we propose a new synthetic image detector that uses features obtained by inverting an open-source pre-trained Stable Diffusion model. We show that these inversion features enable our detector to generalize well to unseen generators of high visual fidelity (e.g. DALL*E 3) even when the detector is trained only on lower fidelity fake images generated via Stable Diffusion. This detector achieves new state-of-the-art across multiple training and evaluation setups. Moreover we introduce a new challenging evaluation protocol that uses reverse image search to mitigate stylistic and thematic biases in the detector evaluation. We show that the resulting evaluation scores align well with detectors' in-the-wild performance and release these datasets as public benchmarks for future research.

In this paper we introduce Fairy a minimalist yet robust adaptation of image-editing diffusion models enhancing them for video editing applications. Our approach centers on the concept of anchor-based cross-frame attention a mechanism that implicitly propagates diffusion features across frames ensuring superior temporal coherence and high-fidelity synthesis. Fairy not only addresses limitations of previous models including memory and processing speed. It also improves temporal consistency through a unique data augmentation strategy. This strategy renders the model equivariant to affine transformations in both source and target images. Remarkably efficient Fairy generates 120-frame 512x384 videos (4-second duration at 30 FPS) in just 14 seconds outpacing prior works by at least 44x. A comprehensive user study involving 1000 generated samples confirms that our approach delivers superior quality decisively outperforming established methods.

Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing attempts to rectify this issue are hindered by the inherent limitations of the pre-trained models and fail to substantially improve demographic diversity. In this work we introduce Fair Retrieval Augmented Generation (FairRAG) a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation. FairRAG enables conditioning through a lightweight linear module that projects reference images into the textual space. To enhance fairness FairRAG applies simple-yet-effective debiasing strategies providing images from diverse demographic groups during the generative process. Extensive experiments demonstrate that FairRAG outperforms existing methods in terms of demographic diversity image-text alignment and image fidelity while incurring minimal computational overhead during inference.

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.

Federated learning (FL) has emerged as a new paradigm for privacy-preserving collaborative training. Under domain skew the current FL approaches are biased and face two fairness problems. 1) Parameter Update Conflict: data disparity among clients leads to varying parameter importance and inconsistent update directions. These two disparities cause important parameters to potentially be overwhelmed by unimportant ones of dominant updates. It consequently results in significant performance decreases for lower-performing clients. 2) Model Aggregation Bias: existing FL approaches introduce unfair weight allocation and neglect domain diversity. It leads to biased model convergence objective and distinct performance among domains. We discover a pronounced directional update consistency in Federated Learning and propose a novel framework to tackle above issues. First leveraging the discovered characteristic we selectively discard unimportant parameter updates to prevent updates from clients with lower performance overwhelmed by unimportant parameters resulting in fairer generalization performance. Second we propose a fair aggregation objective to prevent global model bias towards some domains ensuring that the global model continuously aligns with an unbiased model. The proposed method is generic and can be combined with other existing FL methods to enhance fairness. Comprehensive experiments on Digits and Office-Caltech demonstrate the high fairness and performance of our method.