mlsanityData to 14 Oct 2026

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

arXiv 2203.07740 ↗First posted 15 Mar 2022cs.CVcited by 122

Not on the map. Why?

Abstract (arXiv)

Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging visual learning tasks, which can be cast as a feature distribution matching problem. With the assumption of Gaussian feature distribution, conventional feature distribution matching methods usually match the mean and standard deviation of features. However, the feature distributions of real-world data are usually much more complicated than Gaussian, which cannot be accurately matched by using only the first-order and second-order statistics, while it is computationally prohibitive to use high-order statistics for distribution matching. In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space. Particularly, a fast EHM algorithm, named Sort-Matching, is employed to perform EFDM in a plug-and-play manner with minimal cost. The effectiveness of our proposed EFDM method is verified on a variety of AST and DG tasks, demonstrating new state-of-the-art results. Codes are available at https://github.com/YBZh/EFDM.

Key facts. Cited by 122 papers in the map (data through 14 Oct 2026). Builds on 44 of its 72 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

44 of 72 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  11. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  12. 2020In Search of Lost Domain Generalizationcited by 1,054
32 more
  1. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  2. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  3. 2021Domain Generalization: A Surveycited by 764
  4. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  5. 2021Domain Generalization with MixStylecited by 566
  6. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  7. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  8. 2017Universal Style Transfer via Feature Transformscited by 354
  9. 2016A Learned Representation For Artistic Stylecited by 341
  10. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  11. 2020Learning to Learn Single Domain Generalizationcited by 296
  12. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  13. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 295
  14. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  15. 2018DropBlock: A regularization method for convolutional networkscited by 262
  16. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 246
  17. 2019Episodic Training for Domain Generalizationcited by 245
  18. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  19. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  20. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
  21. 2017Deep Photo Style Transfercited by 168
  22. 2017Demystifying Neural Style Transfercited by 152
  23. 2020Style Normalization and Restitution for Generalizable Person Re-identificationcited by 136
  24. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  25. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  26. 2021Adversarially Adaptive Normalization for Single Domain Generalizationcited by 85
  27. 2017Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Lossescited by 69
  28. 2020Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practicecited by 43
  29. 2019A Closed-form Solution to Universal Style Transfercited by 42
  30. 2021CrossNorm and SelfNorm for Generalization under Distribution Shiftscited by 33
  31. 2021In the light of feature distributions: moment matching for Neural Style Transfercited by 26
  32. 2019Wasserstein Style Transfercited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 20; 2023: 37; 2024: 20; 2025: 31; 2026: 14.

122 papers.

Sort:

By area:

  1. 2022Inversion-Based Style Transfer with Diffusion Modelscited by 291
  2. 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfercited by 196
  3. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 155
  4. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  5. 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
  6. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  7. 2024StyleShot: A Snapshot on Any Stylecited by 62
  8. 2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Modelscited by 52
  9. 2022Compound Domain Generalization via Meta-Knowledge Encodingcited by 40
  10. 2023Anomaly Detection under Distribution Shiftcited by 35
  11. 2025OmniStyle: Filtering High Quality Style Transfer Data at Scalecited by 30
  12. 2023ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalizationcited by 28
38 more
  1. 2023What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locationscited by 25
  2. 2024HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shiftscited by 23
  3. 2023DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalizationcited by 21
  4. 2023StableFDG: Style and Attention Based Learning for Federated Domain Generalizationcited by 21
  5. 2022Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalizationcited by 20
  6. 2022MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfercited by 19
  7. 2022QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelitycited by 18
  8. 2022Bootstrap Generalization Ability from Loss Landscape Perspectivecited by 16
  9. 2022All-to-key Attention for Arbitrary Style Transfercited by 16
  10. 2023Adversarial Style Augmentation for Domain Generalizationcited by 16
  11. 2024UniVST: A Unified Framework for Training-free Localized Video Style Transfercited by 16
  12. 2023Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentationcited by 15
  13. 2023Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylizationcited by 14
  14. 2023Domain Generalisation via Risk Distribution Matchingcited by 14
  15. 2024Uncertainty-guided Contrastive Learning for Single Source Domain Generalisationcited by 14
  16. 2023DEJA VU: Continual Model Generalization For Unseen Domainscited by 13
  17. 2023Learning Dynamic Style Kernels for Artistic Style Transfercited by 12
  18. 2023Painterly Image Harmonization using Diffusion Modelcited by 12
  19. 2022DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluatorcited by 11
  20. 2023Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalizationcited by 11
  21. 2022Domain Generalization with Correlated Style Uncertaintycited by 10
  22. 2023A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learningcited by 10
  23. 2024Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attackcited by 10
  24. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  25. 2023Creative Birds: Self-Supervised Single-View 3D Style Transfercited by 9
  26. 2023Activate and Reject: Towards Safe Domain Generalization under Category Shiftcited by 9
  27. 2024MoreStyle: Relax Low-frequency Constraint of Fourier-based Image Reconstruction in Generalizable Medical Image Segmentationcited by 9
  28. 2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devicescited by 9
  29. 2025AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Modelscited by 9
  30. 2022Causal Inference via Style Transfer for Out-of-distribution Generalisationcited by 8
  31. 2023Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approachcited by 8
  32. 2023NormAUG: Normalization-guided Augmentation for Domain Generalizationcited by 8
  33. 2024Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecastingcited by 7
  34. 2025Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucinationcited by 7
  35. 2022S5Mars: Semi-Supervised Learning for Mars Semantic Segmentationcited by 6
  36. 2023MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learningcited by 6
  37. 2024Towards Combating Frequency Simplicity-biased Learning for Domain Generalizationcited by 6
  38. 2025SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generationcited by 6

50 most cited of 122 All 122 (JSON)