mlsanityData to 14 Oct 2026

A Fourier-based Framework for Domain Generalization

arXiv 2105.11120 ↗First posted 24 May 2021cs.CVcited by 290

Not on the map. Why?

Abstract (arXiv)

Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackling this problem by learning transferable knowledge from multiple source domains in order to generalize to unseen target domains. This paper introduces a novel Fourier-based perspective for domain generalization. The main assumption is that the Fourier phase information contains high-level semantics and is not easily affected by domain shifts. To force the model to capture phase information, we develop a novel Fourier-based data augmentation strategy called amplitude mix which linearly interpolates between the amplitude spectrums of two images. A dual-formed consistency loss called co-teacher regularization is further introduced between the predictions induced from original and augmented images. Extensive experiments on three benchmarks have demonstrated that the proposed method is able to achieve state-of-the-arts performance for domain generalization.

Key facts. Cited by 290 papers in the map (data through 14 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 24 May 2021.

Builds on

39 of 55 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  7. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  8. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  10. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  11. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
27 more
  1. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  2. 2013Domain Generalization via Invariant Feature Representationcited by 623
  3. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  4. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  5. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  6. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  7. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  8. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
  9. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  10. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  11. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  12. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 251
  13. 2019Episodic Training for Domain Generalizationcited by 245
  14. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  15. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  16. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  17. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  18. 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
  19. 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
  20. 2018A Kernel Theory of Modern Data Augmentationcited by 106
  21. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  22. 2020Dual Mixup Regularized Learning for Adversarial Domain Adaptationcited by 99
  23. 2015Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalizationcited by 96
  24. 2020Phase Consistent Ecological Domain Adaptationcited by 62
  25. 2020Informative Dropout for Robust Representation Learning: A Shape-bias Perspectivecited by 57
  26. 2017Adversarial Dropout for Supervised and Semi-supervised Learningcited by 39
  27. 2019Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Datacited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 52; 2023: 81; 2024: 71; 2025: 51; 2026: 19.

290 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  2. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 138
  3. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  4. 2022Improving Vision Transformers by Revisiting High-frequency Componentscited by 76
  5. 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 71
  6. 2023FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Informationcited by 64
  7. 2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
  8. 2024FreqMamba: Viewing Mamba from a Frequency Perspective for Image Derainingcited by 57
  9. 2022Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentationcited by 51
  10. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 48
  11. 2024Frequency-Assisted Mamba for Remote Sensing Image Super-Resolutioncited by 48
  12. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 47
38 more
  1. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 44
  2. 2022Deep Frequency Filtering for Domain Generalizationcited by 43
  3. 2023Meta-causal Learning for Single Domain Generalizationcited by 43
  4. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  5. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  6. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  7. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 39
  8. 2022Attention Consistency on Visual Corruptions for Single-Source Domain Generalizationcited by 37
  9. 2024RobustSAM: Segment Anything Robustly on Degraded Imagescited by 36
  10. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  11. 2022Domain-invariant Feature Exploration for Domain Generalizationcited by 34
  12. 2023Progressive Random Convolutions for Single Domain Generalizationcited by 34
  13. 2023Collaborating Foundation Models for Domain Generalized Semantic Segmentationcited by 34
  14. 2022The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Trainingcited by 33
  15. 2022Generative Domain Adaptation for Face Anti-Spoofingcited by 33
  16. 2024FourierMamba: Fourier Learning Integration with State Space Models for Image Derainingcited by 33
  17. 2021TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learningcited by 32
  18. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  19. 2024Visual Fourier Prompt Tuningcited by 30
  20. 2022Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognitioncited by 29
  21. 2022Attention Diversification for Domain Generalizationcited by 29
  22. 2023ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalizationcited by 28
  23. 2023SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detectioncited by 28
  24. 2023A Simple Recipe for Language-guided Domain Generalized Segmentationcited by 28
  25. 2023Flatness-Aware Minimization for Domain Generalizationcited by 27
  26. 2023Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalizationcited by 26
  27. 2022Test-time Fourier Style Calibration for Domain Generalizationcited by 25
  28. 2023Texture Learning Domain Randomization for Domain Generalized Segmentationcited by 24
  29. 2023Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domainscited by 24
  30. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  31. 2024Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalizationcited by 24
  32. 2023MADG: Margin-based Adversarial Learning for Domain Generalizationcited by 22
  33. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 22
  34. 2022Domain Generalization via Frequency-domain-based Feature Disentanglement and Interactioncited by 21
  35. 2022Cross-Domain Ensemble Distillation for Domain Generalizationcited by 21
  36. 2023FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentationcited by 21
  37. 2023Frequency-mixed Single-source Domain Generalization for Medical Image Segmentationcited by 21
  38. 2023DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalizationcited by 21

50 most cited of 290 All 290 (JSON)