mlsanityData to 14 Oct 2026

Federated Domain Generalization for Image Recognition via Cross-Client Style Transfer

arXiv 2210.00912 ↗First posted 3 Oct 2022cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Domain generalization (DG) has been a hot topic in image recognition, with a goal to train a general model that can perform well on unseen domains. Recently, federated learning (FL), an emerging machine learning paradigm to train a global model from multiple decentralized clients without compromising data privacy, brings new challenges, also new possibilities, to DG. In the FL scenario, many existing state-of-the-art (SOTA) DG methods become ineffective, because they require the centralization of data from different domains during training. In this paper, we propose a novel domain generalization method for image recognition under federated learning through cross-client style transfer (CCST) without exchanging data samples. Our CCST method can lead to more uniform distributions of source clients, and thus make each local model learn to fit the image styles of all the clients to avoid the different model biases. Two types of style (single image style and overall domain style) with corresponding mechanisms are proposed to be chosen according to different scenarios. Our style representation is exceptionally lightweight and can hardly be used for the reconstruction of the dataset. The level of diversity is also flexible to be controlled with a hyper-parameter. Our method outperforms recent SOTA DG methods on two DG benchmarks (PACS, OfficeHome) and a large-scale medical image dataset (Camelyon17) in the FL setting. Last but not least, our method is orthogonal to many classic DG methods, achieving additive performance by combined utilization.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 36 of its 43 references that are in the map. First posted on arXiv 3 Oct 2022.

Builds on

36 of 43 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  8. 2019Invariant Risk Minimizationcited by 1,854
  9. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  10. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  11. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  12. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
24 more
  1. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  2. 2021Domain Generalization with MixStylecited by 566
  3. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  4. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  5. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
  6. 2017Universal Style Transfer via Feature Transformscited by 354
  7. 2016A Learned Representation For Artistic Stylecited by 341
  8. 2021A Fourier-based Framework for Domain Generalizationcited by 290
  9. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  10. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  11. 2019Episodic Training for Domain Generalizationcited by 245
  12. 2017Neural Style Transfer: A Reviewcited by 199
  13. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 174
  14. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  15. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  16. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  17. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  18. 2016Fast Patch-based Style Transfer of Arbitrary Stylecited by 92
  19. 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
  20. 2017Exploring the structure of a real-time, arbitrary neural artistic stylization networkcited by 89
  21. 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79
  22. 2021HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Imagescited by 64
  23. 2017Multi-style Generative Network for Real-time Transfercited by 61
  24. 2017Diversified Texture Synthesis with Feed-forward Networkscited by 59

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 12; 2025: 20; 2026: 1.

40 papers.

Sort:

By area:

  1. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  2. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 48
  3. 2023Federated Domain Generalization: A Surveycited by 25
  4. 2023Robust Visual Question Answering: Datasets, Methods, and Future Challengescited by 23
  5. 2023StableFDG: Style and Attention Based Learning for Federated Domain Generalizationcited by 21
  6. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  7. 2024Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalizationcited by 12
  8. 2022Robust Split Federated Learning for U-shaped Medical Image Networkscited by 11
  9. 2024Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalizationcited by 10
  10. 2024Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradientscited by 7
  11. 2025Federated Domain Generalization with Data-free On-server Matching Gradientcited by 7
  12. 2025FedAlign: Federated Domain Generalization with Cross-Client Feature Alignmentcited by 5
28 more
  1. 2024Feature Diversification and Adaptation for Federated Domain Generalizationcited by 4
  2. 2025Federated Out-of-Distribution Generalization: A Causal Augmentation Viewcited by 4
  3. 2025Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalizationcited by 4
  4. 2024Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic Surgerycited by 3
  5. 2024Boosting Federated Domain Generalization: Understanding the Role of Advanced Pre-Trained Architecturescited by 3
  6. 2025Global Intervention and Distillation for Federated Out-of-Distribution Generalizationcited by 3
  7. 2024FedCCRL: Federated Domain Generalization with Cross-Client Representation Learningcited by 2
  8. 2024Federated Domain Generalization with Label Smoothing and Balanced Decentralized Trainingcited by 2
  9. 2025FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentationcited by 2
  10. 2025FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysiscited by 2
  11. 2025FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classificationcited by 2
  12. 2024Reducing Spurious Correlation for Federated Domain Generalizationcited by 1
  13. 2025Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotioncited by 1
  14. 2025FedS2R: One-Shot Federated Domain Generalization for Synthetic-to-Real Semantic Segmentation in Autonomous Drivingcited by 1
  15. 2026FedStain: Modeling Higher-Order Stain Statistics for Federated Domain Generalization in Computational Pathologycited by 1
  16. 2023FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detectioncited by 0
  17. 2024Federated Learning with New Knowledge: Fundamentals, Advances, and Futurescited by 0
  18. 2024FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuningcited by 0
  19. 2024PARDON: Privacy-Aware and Robust Federated Domain Generalizationcited by 0
  20. 2025WarmFed: Federated Learning with Warm-Start for Globalization and Personalization Via Personalized Diffusion Modelscited by 0
  21. 2025Decentralized Domain Generalization with Style Sharing: Formal Model and Convergence Analysiscited by 0
  22. 2025Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalizationcited by 0
  23. 2025FedSDAF: Leveraging Source Domain Awareness for Enhanced Federated Domain Generalizationcited by 0
  24. 2025Multi-Source Collaborative Style Augmentation and Domain-Invariant Learning for Federated Domain Generalizationcited by 0
  25. 2025ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoningcited by 0
  26. 2025Gains: Fine-grained Federated Domain Adaptation in Open Setcited by 0
  27. 2025TreeFedDG: Alleviating Global Drift in Federated Domain Generalization for Medical Image Segmentationcited by 0
  28. 2025Federated Domain Generalization with Latent Space Inversioncited by 0