mlsanityData to 7 Oct 2026

Domain Generalization with MixStyle

arXiv 2104.02008 ↗First posted 5 Apr 2021cs.CV cs.LGcited by 563

Not on the map. Why?

Abstract (arXiv)

Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain generalization aims to address this problem by learning from a set of source domains a model that is generalizable to any unseen domain. In this paper, a novel approach is proposed based on probabilistically mixing instance-level feature statistics of training samples across source domains. Our method, termed MixStyle, is motivated by the observation that visual domain is closely related to image style (e.g., photo vs.~sketch images). Such style information is captured by the bottom layers of a CNN where our proposed style-mixing takes place. Mixing styles of training instances results in novel domains being synthesized implicitly, which increase the domain diversity of the source domains, and hence the generalizability of the trained model. MixStyle fits into mini-batch training perfectly and is extremely easy to implement. The effectiveness of MixStyle is demonstrated on a wide range of tasks including category classification, instance retrieval and reinforcement learning.

Key facts. Cited by 563 papers in the map (data through 7 Oct 2026). Builds on 48 of its 62 references that are in the map. First posted on arXiv 5 Apr 2021.

Builds on

48 of 62 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  10. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  11. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  12. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
36 more
  1. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  2. 2017Random Erasing Data Augmentationcited by 1,235
  3. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  4. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  5. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  6. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  7. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  8. 2021Domain Generalization: A Surveycited by 760
  9. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  10. 2013Domain Generalization via Invariant Feature Representationcited by 622
  11. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  12. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  13. 2020Reinforcement Learning with Augmented Datacited by 452
  14. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  15. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  16. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  17. 2016A Learned Representation For Artistic Stylecited by 340
  18. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  19. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  20. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  21. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  22. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  23. 2018DropBlock: A regularization method for convolutional networkscited by 261
  24. 2019Episodic Training for Domain Generalizationcited by 245
  25. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  26. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  27. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  28. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 170
  29. 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 160
  30. 2020Domain Adaptive Ensemble Learningcited by 156
  31. 2018Generalization and Regularization in DQNcited by 117
  32. 2019Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learningcited by 102
  33. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
  34. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 80
  35. 2018Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translationcited by 50
  36. 2019Torchreid: A Library for Deep Learning Person Re-Identification in Pytorchcited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 45; 2022: 110; 2023: 139; 2024: 119; 2025: 94; 2026: 56.

563 papers.

Sort:

By area:

  1. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  2. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  3. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
  4. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  5. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  6. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  7. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
  8. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  9. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
  10. 2021Learning Debiased Representation via Disentangled Feature Augmentationcited by 116
  11. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  12. 2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
38 more
  1. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
  2. 2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
  3. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  4. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  5. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  6. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  7. 2022Active Learning by Feature Mixingcited by 63
  8. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
  9. 2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
  10. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  11. 2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
  12. 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 48
  13. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 45
  14. 2022Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentationcited by 44
  15. 2021Semi-Supervised Domain Generalization with Stochastic StyleMatchcited by 43
  16. 2021Source-Free Open Compound Domain Adaptation in Semantic Segmentationcited by 43
  17. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  18. 2023Feature Alignment and Uniformity for Test Time Adaptationcited by 42
  19. 2023Instance-Aware Domain Generalization for Face Anti-Spoofingcited by 42
  20. 2021Federated Learning with Domain Generalizationcited by 41
  21. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  22. 2022Compound Domain Generalization via Meta-Knowledge Encodingcited by 40
  23. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  24. 2023Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimizationcited by 39
  25. 2024CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofingcited by 39
  26. 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
  27. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 38
  28. 2022Multiple-environment Self-adaptive Network for Aerial-view Geo-localizationcited by 37
  29. 2022Attention Consistency on Visual Corruptions for Single-Source Domain Generalizationcited by 37
  30. 2023StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalizationcited by 36
  31. 2023What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?cited by 36
  32. 2023Anomaly Detection under Distribution Shiftcited by 35
  33. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  34. 2022TTTFlow: Unsupervised Test-Time Training with Normalizing Flowcited by 33
  35. 2023Going Beyond Nouns With Vision & Language Models Using Synthetic Datacited by 33
  36. 2024GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusioncited by 33
  37. 2021A Style and Semantic Memory Mechanism for Domain Generalizationcited by 32
  38. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32

50 most cited of 563 All 563 (JSON)