mlsanityData to 7 Oct 2026

Frequency Decomposition to Tap the Potential of Single Domain for Generalization

arXiv 2304.07261 ↗First posted 14 Apr 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Domain generalization (DG), aiming at models able to work on multiple unseen domains, is a must-have characteristic of general artificial intelligence. DG based on single source domain training data is more challenging due to the lack of comparable information to help identify domain invariant features. In this paper, it is determined that the domain invariant features could be contained in the single source domain training samples, then the task is to find proper ways to extract such domain invariant features from the single source domain samples. An assumption is made that the domain invariant features are closely related to the frequency. Then, a new method that learns through multiple frequency domains is proposed. The key idea is, dividing the frequency domain of each original image into multiple subdomains, and learning features in the subdomain by a designed two branches network. In this way, the model is enforced to learn features from more samples of the specifically limited spectrum, which increases the possibility of obtaining the domain invariant features that might have previously been defiladed by easily learned features. Extensive experimental investigation reveals that 1) frequency decomposition can help the model learn features that are difficult to learn. 2) the proposed method outperforms the state-of-the-art methods of single-source domain generalization.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 14 Apr 2023.

Builds on

37 of 46 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  8. 2019Invariant Risk Minimizationcited by 1,832
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  10. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  11. 2021Domain Generalization with MixStylecited by 563
  12. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
25 more
  1. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  2. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  4. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  5. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 360
  6. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  7. 2020Learning to Learn Single Domain Generalizationcited by 295
  8. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  9. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  10. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  11. 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 141
  12. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  13. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  14. 2015Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalizationcited by 96
  15. 2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
  16. 2018Visual Domain Adaptation with Manifold Embedded Distribution Alignmentcited by 91
  17. 2021Adversarially Adaptive Normalization for Single Domain Generalizationcited by 85
  18. 2018Low Frequency Adversarial Perturbationcited by 80
  19. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
  20. 2021Uncertainty-guided Model Generalization to Unseen Domainscited by 41
  21. 2022Deep Frequency Filtering for Domain Generalizationcited by 41
  22. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  23. 2022Attention Consistency on Visual Corruptions for Single-Source Domain Generalizationcited by 37
  24. 2020Feature Alignment and Restoration for Domain Generalization and Adaptationcited by 30
  25. 2020Robust Learning with Frequency Domain Regularizationcited by 1

Built on by

Not cited yet.