2024-05-14 更新
ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning
Authors:Jing Lin, Yao Feng, Weiyang Liu, Michael J. Black
Numerous methods have been proposed to detect, estimate, and analyze properties of people in images, including the estimation of 3D pose, shape, contact, human-object interaction, emotion, and more. Each of these methods works in isolation instead of synergistically. Here we address this problem and build a language-driven human understanding system — ChatHuman, which combines and integrates the skills of many different methods. To do so, we finetune a Large Language Model (LLM) to select and use a wide variety of existing tools in response to user inputs. In doing so, ChatHuman is able to combine information from multiple tools to solve problems more accurately than the individual tools themselves and to leverage tool output to improve its ability to reason about humans. The novel features of ChatHuman include leveraging academic publications to guide the application of 3D human-related tools, employing a retrieval-augmented generation model to generate in-context-learning examples for handling new tools, and discriminating and integrating tool results to enhance 3D human understanding. Our experiments show that ChatHuman outperforms existing models in both tool selection accuracy and performance across multiple 3D human-related tasks. ChatHuman is a step towards consolidating diverse methods for human analysis into a single, powerful, system for 3D human reasoning.
PDF Project page: https://chathuman.github.io
点此查看论文截图
Tactile-Augmented Radiance Fields
Authors:Yiming Dou, Fengyu Yang, Yi Liu, Antonio Loquercio, Andrew Owens
We present a scene representation, which we call a tactile-augmented radiance field (TaRF), that brings vision and touch into a shared 3D space. This representation can be used to estimate the visual and tactile signals for a given 3D position within a scene. We capture a scene’s TaRF from a collection of photos and sparsely sampled touch probes. Our approach makes use of two insights: (i) common vision-based touch sensors are built on ordinary cameras and thus can be registered to images using methods from multi-view geometry, and (ii) visually and structurally similar regions of a scene share the same tactile features. We use these insights to register touch signals to a captured visual scene, and to train a conditional diffusion model that, provided with an RGB-D image rendered from a neural radiance field, generates its corresponding tactile signal. To evaluate our approach, we collect a dataset of TaRFs. This dataset contains more touch samples than previous real-world datasets, and it provides spatially aligned visual signals for each captured touch signal. We demonstrate the accuracy of our cross-modal generative model and the utility of the captured visual-tactile data on several downstream tasks. Project page: https://dou-yiming.github.io/TaRF
PDF CVPR 2024, Project page: https://dou-yiming.github.io/TaRF, Code: https://github.com/Dou-Yiming/TaRF/
点此查看论文截图
Fast LiDAR Upsampling using Conditional Diffusion Models
Authors:Sander Elias Magnussen Helgesen, Kazuto Nakashima, Jim Tørresen, Ryo Kurazume
The search for refining 3D LiDAR data has attracted growing interest motivated by recent techniques such as supervised learning or generative model-based methods. Existing approaches have shown the possibilities for using diffusion models to generate refined LiDAR data with high fidelity, although the performance and speed of such methods have been limited. These limitations make it difficult to execute in real-time, causing the approaches to struggle in real-world tasks such as autonomous navigation and human-robot interaction. In this work, we introduce a novel approach based on conditional diffusion models for fast and high-quality sparse-to-dense upsampling of 3D scene point clouds through an image representation. Our method employs denoising diffusion probabilistic models trained with conditional inpainting masks, which have been shown to give high performance on image completion tasks. We introduce a series of experiments, including multiple datasets, sampling steps, and conditional masks, to determine the ideal configuration, striking a balance between performance and inference speed. This paper illustrates that our method outperforms the baselines in sampling speed and quality on upsampling tasks using the KITTI-360 dataset. Furthermore, we illustrate the generalization ability of our approach by simultaneously training on real-world and synthetic datasets, introducing variance in quality and environments.
PDF
点此查看论文截图
NeRFFaceSpeech: One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior
Authors:Gihoon Kim, Kwanggyoon Seo, Sihun Cha, Junyong Noh
Audio-driven talking head generation is advancing from 2D to 3D content. Notably, Neural Radiance Field (NeRF) is in the spotlight as a means to synthesize high-quality 3D talking head outputs. Unfortunately, this NeRF-based approach typically requires a large number of paired audio-visual data for each identity, thereby limiting the scalability of the method. Although there have been attempts to generate audio-driven 3D talking head animations with a single image, the results are often unsatisfactory due to insufficient information on obscured regions in the image. In this paper, we mainly focus on addressing the overlooked aspect of 3D consistency in the one-shot, audio-driven domain, where facial animations are synthesized primarily in front-facing perspectives. We propose a novel method, NeRFFaceSpeech, which enables to produce high-quality 3D-aware talking head. Using prior knowledge of generative models combined with NeRF, our method can craft a 3D-consistent facial feature space corresponding to a single image. Our spatial synchronization method employs audio-correlated vertex dynamics of a parametric face model to transform static image features into dynamic visuals through ray deformation, ensuring realistic 3D facial motion. Moreover, we introduce LipaintNet that can replenish the lacking information in the inner-mouth area, which can not be obtained from a given single image. The network is trained in a self-supervised manner by utilizing the generative capabilities without additional data. The comprehensive experiments demonstrate the superiority of our method in generating audio-driven talking heads from a single image with enhanced 3D consistency compared to previous approaches. In addition, we introduce a quantitative way of measuring the robustness of a model against pose changes for the first time, which has been possible only qualitatively.
PDF 11 pages, 5 figures
点此查看论文截图
MasterWeaver: Taming Editability and Identity for Personalized Text-to-Image Generation
Authors:Yuxiang Wei, Zhilong Ji, Jinfeng Bai, Hongzhi Zhang, Lei Zhang, Wangmeng Zuo
Text-to-image (T2I) diffusion models have shown significant success in personalized text-to-image generation, which aims to generate novel images with human identities indicated by the reference images. Despite promising identity fidelity has been achieved by several tuning-free methods, they usually suffer from overfitting issues. The learned identity tends to entangle with irrelevant information, resulting in unsatisfied text controllability, especially on faces. In this work, we present MasterWeaver, a test-time tuning-free method designed to generate personalized images with both faithful identity fidelity and flexible editability. Specifically, MasterWeaver adopts an encoder to extract identity features and steers the image generation through additional introduced cross attention. To improve editability while maintaining identity fidelity, we propose an editing direction loss for training, which aligns the editing directions of our MasterWeaver with those of the original T2I model. Additionally, a face-augmented dataset is constructed to facilitate disentangled identity learning, and further improve the editability. Extensive experiments demonstrate that our MasterWeaver can not only generate personalized images with faithful identity, but also exhibit superiority in text controllability. Our code will be publicly available at https://github.com/csyxwei/MasterWeaver.
PDF 34 pages
点此查看论文截图
Frame Interpolation with Consecutive Brownian Bridge Diffusion
Authors:Zonglin Lyu, Ming Li, Jianbo Jiao, Chen Chen
Recent work in Video Frame Interpolation (VFI) tries to formulate VFI as a diffusion-based conditional image generation problem, synthesizing the intermediate frame given a random noise and neighboring frames. Due to the relatively high resolution of videos, Latent Diffusion Models (LDMs) are employed as the conditional generation model, where the autoencoder compresses images into latent representations for diffusion and then reconstructs images from these latent representations. Such a formulation poses a crucial challenge: VFI expects that the output is deterministically equal to the ground truth intermediate frame, but LDMs randomly generate a diverse set of different images when the model runs multiple times. The reason for the diverse generation is that the cumulative variance (variance accumulated at each step of generation) of generated latent representations in LDMs is large. This makes the sampling trajectory random, resulting in diverse rather than deterministic generations. To address this problem, we propose our unique solution: Frame Interpolation with Consecutive Brownian Bridge Diffusion. Specifically, we propose consecutive Brownian Bridge diffusion that takes a deterministic initial value as input, resulting in a much smaller cumulative variance of generated latent representations. Our experiments suggest that our method can improve together with the improvement of the autoencoder and achieve state-of-the-art performance in VFI, leaving strong potential for further enhancement.
PDF
点此查看论文截图
PUMA: margin-based data pruning
Authors:Javier Maroto, Pascal Frossard
Deep learning has been able to outperform humans in terms of classification accuracy in many tasks. However, to achieve robustness to adversarial perturbations, the best methodologies require to perform adversarial training on a much larger training set that has been typically augmented using generative models (e.g., diffusion models). Our main objective in this work, is to reduce these data requirements while achieving the same or better accuracy-robustness trade-offs. We focus on data pruning, where some training samples are removed based on the distance to the model classification boundary (i.e., margin). We find that the existing approaches that prune samples with low margin fails to increase robustness when we add a lot of synthetic data, and explain this situation with a perceptron learning task. Moreover, we find that pruning high margin samples for better accuracy increases the harmful impact of mislabeled perturbed data in adversarial training, hurting both robustness and accuracy. We thus propose PUMA, a new data pruning strategy that computes the margin using DeepFool, and prunes the training samples of highest margin without hurting performance by jointly adjusting the training attack norm on the samples of lowest margin. We show that PUMA can be used on top of the current state-of-the-art methodology in robustness, and it is able to significantly improve the model performance unlike the existing data pruning strategies. Not only PUMA achieves similar robustness with less data, but it also significantly increases the model accuracy, improving the performance trade-off.
PDF
点此查看论文截图
Controllable Image Generation With Composed Parallel Token Prediction
Authors:Jamie Stirling, Noura Al-Moubayed
Compositional image generation requires models to generalise well in situations where two or more input concepts do not necessarily appear together in training (compositional generalisation). Despite recent progress in compositional image generation via composing continuous sampling processes such as diffusion and energy-based models, composing discrete generative processes has remained an open challenge, with the promise of providing improvements in efficiency, interpretability and simplicity. To this end, we propose a formulation for controllable conditional generation of images via composing the log-probability outputs of discrete generative models of the latent space. Our approach, when applied alongside VQ-VAE and VQ-GAN, achieves state-of-the-art generation accuracy in three distinct settings (FFHQ, Positional CLEVR and Relational CLEVR) while attaining competitive Fr\’echet Inception Distance (FID) scores. Our method attains an average generation accuracy of $80.71\%$ across the studied settings. Our method also outperforms the next-best approach (ranked by accuracy) in terms of FID in seven out of nine experiments, with an average FID of $24.23$ (an average improvement of $-9.58$). Furthermore, our method offers a $2.3\times$ to $12\times$ speedup over comparable continuous compositional methods on our hardware. We find that our method can generalise to combinations of input conditions that lie outside the training data (e.g. more objects per image) in addition to offering an interpretable dimension of controllability via concept weighting. We further demonstrate that our approach can be readily applied to an open pre-trained discrete text-to-image model without any fine-tuning, allowing for fine-grained control of text-to-image generation.
PDF 9 pages, 6 figures, non-anonymised pre-print for NeurIPS 2024 main conference. arXiv admin note: text overlap with arXiv:2402.04550, arXiv:2404.13788, arXiv:2403.06098, arXiv:2401.16025
点此查看论文截图
OneTo3D: One Image to Re-editable Dynamic 3D Model and Video Generation
Authors:Jinwei Lin
One image to editable dynamic 3D model and video generation is novel direction and change in the research area of single image to 3D representation or 3D reconstruction of image. Gaussian Splatting has demonstrated its advantages in implicit 3D reconstruction, compared with the original Neural Radiance Fields. As the rapid development of technologies and principles, people tried to used the Stable Diffusion models to generate targeted models with text instructions. However, using the normal implicit machine learning methods is hard to gain the precise motions and actions control, further more, it is difficult to generate a long content and semantic continuous 3D video. To address this issue, we propose the OneTo3D, a method and theory to used one single image to generate the editable 3D model and generate the targeted semantic continuous time-unlimited 3D video. We used a normal basic Gaussian Splatting model to generate the 3D model from a single image, which requires less volume of video memory and computer calculation ability. Subsequently, we designed an automatic generation and self-adaptive binding mechanism for the object armature. Combined with the re-editable motions and actions analyzing and controlling algorithm we proposed, we can achieve a better performance than the SOTA projects in the area of building the 3D model precise motions and actions control, and generating a stable semantic continuous time-unlimited 3D video with the input text instructions. Here we will analyze the detailed implementation methods and theories analyses. Relative comparisons and conclusions will be presented. The project code is open source.
PDF 24 pages, 13 figures, 2 tables
点此查看论文截图
Shape Conditioned Human Motion Generation with Diffusion Model
Authors:Kebing Xue, Hyewon Seo
Human motion synthesis is an important task in computer graphics and computer vision. While focusing on various conditioning signals such as text, action class, or audio to guide the generation process, most existing methods utilize skeleton-based pose representation, requiring additional skinning to produce renderable meshes. Given that human motion is a complex interplay of bones, joints, and muscles, considering solely the skeleton for generation may neglect their inherent interdependency, which can limit the variability and precision of the generated results. To address this issue, we propose a Shape-conditioned Motion Diffusion model (SMD), which enables the generation of motion sequences directly in mesh format, conditioned on a specified target mesh. In SMD, the input meshes are transformed into spectral coefficients using graph Laplacian, to efficiently represent meshes. Subsequently, we propose a Spectral-Temporal Autoencoder (STAE) to leverage cross-temporal dependencies within the spectral domain. Extensive experimental evaluations show that SMD not only produces vivid and realistic motions but also achieves competitive performance in text-to-motion and action-to-motion tasks when compared to state-of-the-art methods.
PDF
点此查看论文截图
Semantic Guided Large Scale Factor Remote Sensing Image Super-resolution with Generative Diffusion Prior
Authors:Ce Wang, Wanjie Sun
Remote sensing images captured by different platforms exhibit significant disparities in spatial resolution. Large scale factor super-resolution (SR) algorithms are vital for maximizing the utilization of low-resolution (LR) satellite data captured from orbit. However, existing methods confront challenges in recovering SR images with clear textures and correct ground objects. We introduce a novel framework, the Semantic Guided Diffusion Model (SGDM), designed for large scale factor remote sensing image super-resolution. The framework exploits a pre-trained generative model as a prior to generate perceptually plausible SR images. We further enhance the reconstruction by incorporating vector maps, which carry structural and semantic cues. Moreover, pixel-level inconsistencies in paired remote sensing images, stemming from sensor-specific imaging characteristics, may hinder the convergence of the model and diversity in generated results. To address this problem, we propose to extract the sensor-specific imaging characteristics and model the distribution of them, allowing diverse SR images generation based on imaging characteristics provided by reference images or sampled from the imaging characteristic probability distributions. To validate and evaluate our approach, we create the Cross-Modal Super-Resolution Dataset (CMSRD). Qualitative and quantitative experiments on CMSRD showcase the superiority and broad applicability of our method. Experimental results on downstream vision tasks also demonstrate the utilitarian of the generated SR images. The dataset and code will be publicly available at https://github.com/wwangcece/SGDM
PDF
点此查看论文截图
Retrieval Enhanced Zero-Shot Video Captioning
Authors:Yunchuan Ma, Laiyun Qing, Guorong Li, Yuankai Qi, Quan Z. Sheng, Qingming Huang
Despite the significant progress of fully-supervised video captioning, zero-shot methods remain much less explored. In this paper, we propose to take advantage of existing pre-trained large-scale vision and language models to directly generate captions with test time adaptation. Specifically, we bridge video and text using three key models: a general video understanding model XCLIP, a general image understanding model CLIP, and a text generation model GPT-2, due to their source-code availability. The main challenge is how to enable the text generation model to be sufficiently aware of the content in a given video so as to generate corresponding captions. To address this problem, we propose using learnable tokens as a communication medium between frozen GPT-2 and frozen XCLIP as well as frozen CLIP. Differing from the conventional way to train these tokens with training data, we update these tokens with pseudo-targets of the inference data under several carefully crafted loss functions which enable the tokens to absorb video information catered for GPT-2. This procedure can be done in just a few iterations (we use 16 iterations in the experiments) and does not require ground truth data. Extensive experimental results on three widely used datasets, MSR-VTT, MSVD, and VATEX, show 4% to 20% improvements in terms of the main metric CIDEr compared to the existing state-of-the-art methods.
PDF
点此查看论文截图
Modeling Pedestrian Intrinsic Uncertainty for Multimodal Stochastic Trajectory Prediction via Energy Plan Denoising
Authors:Yao Liu, Quan Z. Sheng, Lina Yao
Pedestrian trajectory prediction plays a pivotal role in the realms of autonomous driving and smart cities. Despite extensive prior research employing sequence and generative models, the unpredictable nature of pedestrians, influenced by their social interactions and individual preferences, presents challenges marked by uncertainty and multimodality. In response, we propose the Energy Plan Denoising (EPD) model for stochastic trajectory prediction. EPD initially provides a coarse estimation of the distribution of future trajectories, termed the Plan, utilizing the Langevin Energy Model. Subsequently, it refines this estimation through denoising via the Probabilistic Diffusion Model. By initiating denoising with the Plan, EPD effectively reduces the need for iterative steps, thereby enhancing efficiency. Furthermore, EPD differs from conventional approaches by modeling the distribution of trajectories instead of individual trajectories. This allows for the explicit modeling of pedestrian intrinsic uncertainties and eliminates the need for multiple denoising operations. A single denoising operation produces a distribution from which multiple samples can be drawn, significantly enhancing efficiency. Moreover, EPD’s fine-tuning of the Plan contributes to improved model performance. We validate EPD on two publicly available datasets, where it achieves state-of-the-art results. Additionally, ablation experiments underscore the contributions of individual modules, affirming the efficacy of the proposed approach.
PDF
点此查看论文截图
Understanding and Evaluating Human Preferences for AI Generated Images with Instruction Tuning
Authors:Jiarui Wang, Huiyu Duan, Guangtao Zhai, Xiongkuo Min
Artificial Intelligence Generated Content (AIGC) has grown rapidly in recent years, among which AI-based image generation has gained widespread attention due to its efficient and imaginative image creation ability. However, AI-generated Images (AIGIs) may not satisfy human preferences due to their unique distortions, which highlights the necessity to understand and evaluate human preferences for AIGIs. To this end, in this paper, we first establish a novel Image Quality Assessment (IQA) database for AIGIs, termed AIGCIQA2023+, which provides human visual preference scores and detailed preference explanations from three perspectives including quality, authenticity, and correspondence. Then, based on the constructed AIGCIQA2023+ database, this paper presents a MINT-IQA model to evaluate and explain human preferences for AIGIs from Multi-perspectives with INstruction Tuning. Specifically, the MINT-IQA model first learn and evaluate human preferences for AI-generated Images from multi-perspectives, then via the vision-language instruction tuning strategy, MINT-IQA attains powerful understanding and explanation ability for human visual preference on AIGIs, which can be used for feedback to further improve the assessment capabilities. Extensive experimental results demonstrate that the proposed MINT-IQA model achieves state-of-the-art performance in understanding and evaluating human visual preferences for AIGIs, and the proposed model also achieves competing results on traditional IQA tasks compared with state-of-the-art IQA models. The AIGCIQA2023+ database and MINT-IQA model will be released to facilitate future research.
PDF
点此查看论文截图
GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting
Authors:Haodong Chen, Yongle Huang, Haojian Huang, Xiangsheng Ge, Dian Shao
The increasing prominence of e-commerce has underscored the importance of Virtual Try-On (VTON). However, previous studies predominantly focus on the 2D realm and rely heavily on extensive data for training. Research on 3D VTON primarily centers on garment-body shape compatibility, a topic extensively covered in 2D VTON. Thanks to advances in 3D scene editing, a 2D diffusion model has now been adapted for 3D editing via multi-viewpoint editing. In this work, we propose GaussianVTON, an innovative 3D VTON pipeline integrating Gaussian Splatting (GS) editing with 2D VTON. To facilitate a seamless transition from 2D to 3D VTON, we propose, for the first time, the use of only images as editing prompts for 3D editing. To further address issues, e.g., face blurring, garment inaccuracy, and degraded viewpoint quality during editing, we devise a three-stage refinement strategy to gradually mitigate potential issues. Furthermore, we introduce a new editing strategy termed Edit Recall Reconstruction (ERR) to tackle the limitations of previous editing strategies in leading to complex geometric changes. Our comprehensive experiments demonstrate the superiority of GaussianVTON, offering a novel perspective on 3D VTON while also establishing a novel starting point for image-prompting 3D scene editing.
PDF On-going work
点此查看论文截图
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Authors:Hanshu Yan, Xingchao Liu, Jiachun Pan, Jun Hao Liew, Qiang Liu, Jiashi Feng
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via the reflow operation, thereby approaching piecewise linear flows. PeRFlow achieves superior performance in a few-step generation. Moreover, through dedicated parameterizations, the obtained PeRFlow models show advantageous transfer ability, serving as universal plug-and-play accelerators that are compatible with various workflows based on the pre-trained diffusion models. The implementations of training and inference are fully open-sourced. https://github.com/magic-research/piecewise-rectified-flow
PDF
点此查看论文截图
CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution
Authors:Qingguo Liu, Chenyi Zhuang, Pan Gao, Jie Qin
Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details. In this paper, we propose a novel BSR approach, Content-aware Degradation-driven Transformer (CDFormer), to capture both degradation and content representations. However, low-resolution images cannot provide enough content details, and thus we introduce a diffusion-based module $CDFormer{diff}$ to first learn Content Degradation Prior (CDP) in both low- and high-resolution images, and then approximate the real distribution given only low-resolution information. Moreover, we apply an adaptive SR network $CDFormer{SR}$ that effectively utilizes CDP to refine features. Compared to previous diffusion-based SR methods, we treat the diffusion model as an estimator that can overcome the limitations of expensive sampling time and excessive diversity. Experiments show that CDFormer can outperform existing methods, establishing a new state-of-the-art performance on various benchmarks under blind settings. Codes and models will be available at \href{https://github.com/I2-Multimedia-Lab/CDFormer}{https://github.com/I2-Multimedia-Lab/CDFormer}.
PDF
点此查看论文截图
SAR Image Synthesis with Diffusion Models
Authors:Denisa Qosja, Simon Wagner, Daniel O’Hagan
In recent years, diffusion models (DMs) have become a popular method for generating synthetic data. By achieving samples of higher quality, they quickly became superior to generative adversarial networks (GANs) and the current state-of-the-art method in generative modeling. However, their potential has not yet been exploited in radar, where the lack of available training data is a long-standing problem. In this work, a specific type of DMs, namely denoising diffusion probabilistic model (DDPM) is adapted to the SAR domain. We investigate the network choice and specific diffusion parameters for conditional and unconditional SAR image generation. In our experiments, we show that DDPM qualitatively and quantitatively outperforms state-of-the-art GAN-based methods for SAR image generation. Finally, we show that DDPM profits from pretraining on largescale clutter data, generating SAR images of even higher quality.
PDF Published at IEEE Radar Conference 2024
点此查看论文截图
CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models
Authors:Nick Stracke, Stefan Andreas Baumann, Joshua M. Susskind, Miguel Angel Bautista, Björn Ommer
Text-to-image generative models have become a prominent and powerful tool that excels at generating high-resolution realistic images. However, guiding the generative process of these models to consider detailed forms of conditioning reflecting style and/or structure information remains an open problem. In this paper, we present LoRAdapter, an approach that unifies both style and structure conditioning under the same formulation using a novel conditional LoRA block that enables zero-shot control. LoRAdapter is an efficient, powerful, and architecture-agnostic approach to condition text-to-image diffusion models, which enables fine-grained control conditioning during generation and outperforms recent state-of-the-art approaches
PDF
点此查看论文截图
Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data
Authors:Mahdi Morafah, Matthias Reisser, Bill Lin, Christos Louizos
The proliferation of edge devices has brought Federated Learning (FL) to the forefront as a promising paradigm for decentralized and collaborative model training while preserving the privacy of clients’ data. However, FL struggles with a significant performance reduction and poor convergence when confronted with Non-Independent and Identically Distributed (Non-IID) data distributions among participating clients. While previous efforts, such as client drift mitigation and advanced server-side model fusion techniques, have shown some success in addressing this challenge, they often overlook the root cause of the performance reduction - the absence of identical data accurately mirroring the global data distribution among clients. In this paper, we introduce Gen-FedSD, a novel approach that harnesses the powerful capability of state-of-the-art text-to-image foundation models to bridge the significant Non-IID performance gaps in FL. In Gen-FedSD, each client constructs textual prompts for each class label and leverages an off-the-shelf state-of-the-art pre-trained Stable Diffusion model to synthesize high-quality data samples. The generated synthetic data is tailored to each client’s unique local data gaps and distribution disparities, effectively making the final augmented local data IID. Through extensive experimentation, we demonstrate that Gen-FedSD achieves state-of-the-art performance and significant communication cost savings across various datasets and Non-IID settings.
PDF International Workshop on Federated Foundation Models for the Web 2024 (FL@FM-TheWebConf’24)
点此查看论文截图