mlsanityData to 7 Oct 2026

Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning

arXiv 2203.07656 ↗First posted 15 Mar 2022cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Previous few-shot learning (FSL) works mostly are limited to natural images of general concepts and categories. These works assume very high visual similarity between the source and target classes. In contrast, the recently proposed cross-domain few-shot learning (CD-FSL) aims at transferring knowledge from general nature images of many labeled examples to novel domain-specific target categories of only a few labeled examples. The key challenge of CD-FSL lies in the huge data shift between source and target domains, which is typically in the form of totally different visual styles. This makes it very nontrivial to directly extend the classical FSL methods to address the CD-FSL task. To this end, this paper studies the problem of CD-FSL by spanning the style distributions of the source dataset. Particularly, wavelet transform is introduced to enable the decomposition of visual representations into low-frequency components such as shape and style and high-frequency components e.g., texture. To make our model robust to visual styles, the source images are augmented by swapping the styles of their low-frequency components with each other. We propose a novel Style Augmentation (StyleAug) module to implement this idea. Furthermore, we present a Self-Supervised Learning (SSL) module to ensure the predictions of style-augmented images are semantically similar to the unchanged ones. This avoids the potential semantic drift problem in exchanging the styles. Extensive experiments on two CD-FSL benchmarks show the effectiveness of our method. Our codes and models will be released.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 46 of its 73 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

46 of 73 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  12. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
34 more
  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  2. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  3. 2019A Closer Look at Few-shot Classificationcited by 679
  4. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  5. 2021Domain Generalization with MixStylecited by 563
  6. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  9. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  10. 2017Meta Networkscited by 268
  11. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
  12. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  13. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  14. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  15. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  16. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  17. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  18. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  19. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  20. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  21. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  22. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  23. 2019Self-Supervised Learning For Few-Shot Image Classificationcited by 44
  24. 2020Cross-Domain Few-Shot Learning by Representation Fusioncited by 32
  25. 2019Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolutioncited by 30
  26. 2021SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurringcited by 26
  27. 2016Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplificationcited by 22
  28. 2017Wavelet Convolutional Neural Networks for Texture Classificationcited by 21
  29. 2020Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classificationcited by 20
  30. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  31. 2020Remove Appearance Shift for Ultrasound Image Segmentation via Fast and Universal Style Transfercited by 8
  32. 2020Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learningcited by 8
  33. 2021DAMSL: Domain Agnostic Meta Score-based Learningcited by 4
  34. 2021SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 5; 2025: 8; 2026: 5.

23 papers.

Sort:

By area:

  1. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  2. 2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
  3. 2025EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answeringcited by 19
  4. 2022TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learningcited by 16
  5. 2025EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmarkcited by 16
  6. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  7. 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detectioncited by 14
  8. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
  9. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  10. 2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learningcited by 9
  11. 2024Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Promptingcited by 9
  12. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
11 more
  1. 2026Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learningcited by 5
  2. 2026Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learningcited by 4
  3. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  4. 2025Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservationcited by 2
  5. 2026Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learningcited by 2
  6. 2025FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learningcited by 1
  7. 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detectioncited by 1
  8. 2025MetaLab: Few-Shot Game Changer for Image Recognitioncited by 0
  9. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  10. 2025FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learningcited by 0
  11. 2026When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learningcited by 0