mlsanityData to 7 Oct 2026

FSDR: Frequency Space Domain Randomization for Domain Generalization

arXiv 2103.02370 ↗First posted 3 Mar 2021cs.CVcited by 163

Not on the map. Why?

Abstract (arXiv)

Domain generalization aims to learn a generalizable model from a known source domain for various unknown target domains. It has been studied widely by domain randomization that transfers source images to different styles in spatial space for learning domain-agnostic features. However, most existing randomization uses GANs that often lack of controls and even alter semantic structures of images undesirably. Inspired by the idea of JPEG that converts spatial images into multiple frequency components (FCs), we propose Frequency Space Domain Randomization (FSDR) that randomizes images in frequency space by keeping domain-invariant FCs (DIFs) and randomizing domain-variant FCs (DVFs) only. FSDR has two unique features: 1) it decomposes images into DIFs and DVFs which allows explicit access and manipulation of them and more controllable randomization; 2) it has minimal effects on semantic structures of images and domain-invariant features. We examined domain variance and invariance property of FCs statistically and designed a network that can identify and fuse DIFs and DVFs dynamically through iterative learning. Extensive experiments over multiple domain generalizable segmentation tasks show that FSDR achieves superior segmentation and its performance is even on par with domain adaptation methods that access target data in training.

Key facts. Cited by 163 papers in the map (data through 7 Oct 2026). Builds on 65 of its 88 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

65 of 88 references.

References · 65

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  11. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  12. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
38 more
  1. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  2. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  3. 2013Domain Generalization via Invariant Feature Representationcited by 622
  4. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  5. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  6. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  7. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  8. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  9. 2019Confidence Regularized Self-Trainingcited by 418
  10. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  11. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  12. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  13. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  14. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  15. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  16. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  17. 2020Learning to Learn Single Domain Generalizationcited by 295
  18. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  19. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  20. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  21. 2019Episodic Training for Domain Generalizationcited by 245
  22. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
  23. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  24. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  25. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  26. 2020Learning in the Frequency Domaincited by 196
  27. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  28. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  29. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  30. 2019Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationcited by 133
  31. 2017Adversarial Dropout Regularizationcited by 106
  32. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  33. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 94
  34. 2018Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Datacited by 94
  35. 2018Best sources forward: domain generalization through source-specific netscited by 81
  36. 2020Contextual-Relation Consistent Domain Adaptation for Semantic Segmentationcited by 70
  37. 2020Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentationcited by 62
  38. 2021Uncertainty-Aware Unsupervised Domain Adaptation in Object Detectioncited by 59

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 33; 2023: 43; 2024: 26; 2025: 31; 2026: 10.

163 papers.

Sort:

By area:

  1. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  2. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
  3. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  4. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  5. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  6. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  7. 2021RDA: Robust Domain Adaptation via Fourier Adversarial Attackingcited by 48
  8. 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 48
  9. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  10. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  11. 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Controlcited by 44
  12. 2021Source-Free Open Compound Domain Adaptation in Semantic Segmentationcited by 43
38 more
  1. 2022Deep Frequency Filtering for Domain Generalizationcited by 41
  2. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  3. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  4. 2023A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidancecited by 40
  5. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 38
  6. 2021Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentationcited by 36
  7. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  8. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  9. 2023Collaborating Foundation Models for Domain Generalized Semantic Segmentationcited by 33
  10. 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentationcited by 30
  11. 2021Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillationcited by 28
  12. 2022Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domaincited by 28
  13. 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 27
  14. 2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
  15. 2021WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentationcited by 25
  16. 2021DA-DETR: Domain Adaptive Detection Transformer with Information Fusioncited by 24
  17. 2023Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domainscited by 24
  18. 2023Texture Learning Domain Randomization for Domain Generalized Segmentationcited by 23
  19. 2022Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalizationcited by 22
  20. 2021Domain Adaptive Video Segmentation via Temporal Consistency Regularizationcited by 21
  21. 2022Domain Generalization via Frequency-domain-based Feature Disentanglement and Interactioncited by 21
  22. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 21
  23. 2024Historical Test-time Prompt Tuning for Vision Foundation Modelscited by 21
  24. 2022An Annotation-free Restoration Network for Cataractous Fundus Imagescited by 20
  25. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
  26. 2022Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagerycited by 19
  27. 2023DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentationcited by 19
  28. 2023Domain Generalization via Balancing Training Difficulty and Model Capabilitycited by 19
  29. 2022Intra-Source Style Augmentation for Improved Domain Generalizationcited by 17
  30. 2024Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learningcited by 17
  31. 2021MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentationcited by 16
  32. 2021Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentationcited by 15
  33. 2022Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglementcited by 15
  34. 2022Label-Efficient Domain Generalization via Collaborative Exploration and Generalizationcited by 15
  35. 2025FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentationcited by 15
  36. 2021GenCo: Generative Co-training for Generative Adversarial Networks with Limited Datacited by 14
  37. 2023Learning to Distill Global Representation for Sparse-View CTcited by 14
  38. 2025FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasingcited by 14

50 most cited of 163 All 163 (JSON)