mlsanityData to 7 Oct 2026

FDA: Fourier Domain Adaptation for Semantic Segmentation

arXiv 2004.05498 ↗First posted 11 Apr 2020cs.CVcited by 540

Not on the map. Why?

Abstract (arXiv)

We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate the method in semantic segmentation, where densely annotated images are aplenty in one domain (synthetic data), but difficult to obtain in another (real images). Current state-of-the-art methods are complex, some requiring adversarial optimization to render the backbone of a neural network invariant to the discrete domain selection variable. Our method does not require any training to perform the domain alignment, just a simple Fourier Transform and its inverse. Despite its simplicity, it achieves state-of-the-art performance in the current benchmarks, when integrated into a relatively standard semantic segmentation model. Our results indicate that even simple procedures can discount nuisance variability in the data that more sophisticated methods struggle to learn away.

Key facts. Cited by 540 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 92; 2022: 127; 2023: 128; 2024: 80; 2025: 68; 2026: 45.

540 papers.

Sort:

By area:

  1. 2022Continual Test-Time Domain Adaptationcited by 520
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  3. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  4. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  5. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  6. 2021Global Filter Networks for Image Classificationcited by 257
  7. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  8. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  9. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  10. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  11. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  12. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
38 more
  1. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  2. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  3. 2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
  4. 2021Intriguing Findings of Frequency Selection for Image Deblurringcited by 80
  5. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  6. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  7. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  8. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 71
  9. 2022Mitosis domain generalization in histopathology images -- The MIDOG challengecited by 66
  10. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  11. 2021FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysiscited by 60
  12. 2022PODA: Prompt-driven Zero-shot Domain Adaptationcited by 60
  13. 2022Balancing Discriminability and Transferability for Source-Free Domain Adaptationcited by 58
  14. 2024FreqMamba: Viewing Mamba from a Frequency Perspective for Image Derainingcited by 57
  15. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 56
  16. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  17. 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
  18. 2021RDA: Robust Domain Adaptation via Fourier Adversarial Attackingcited by 48
  19. 2022Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentationcited by 47
  20. 2024Frequency-Assisted Mamba for Remote Sensing Image Super-Resolutioncited by 47
  21. 2022Cross Domain Object Detection by Target-Perceived Dual Branch Distillationcited by 46
  22. 2022Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentationcited by 46
  23. 2023Unmasking Anomalies in Road-Scene Segmentationcited by 45
  24. 2021Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentationcited by 44
  25. 2022A Probabilistic Framework for Lifelong Test-Time Adaptationcited by 44
  26. 2021Multi-Target Domain Adaptation with Collaborative Consistency Learningcited by 43
  27. 2021Source-Free Open Compound Domain Adaptation in Semantic Segmentationcited by 43
  28. 2021Cross-View Regularization for Domain Adaptive Panoptic Segmentationcited by 41
  29. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  30. 2022Deep Frequency Filtering for Domain Generalizationcited by 41
  31. 2022PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentationcited by 41
  32. 2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
  33. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  34. 2023All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenescited by 40
  35. 2025BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster responsecited by 39
  36. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 38
  37. 2022Attention Consistency on Visual Corruptions for Single-Source Domain Generalizationcited by 37
  38. 2021Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularizationcited by 36

50 most cited of 540 All 540 (JSON)