mlsanityData to 7 Oct 2026

StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

arXiv 2302.09309 ↗First posted 18 Feb 2023cs.CVcited by 53

Not on the map. Why?

Abstract (arXiv)

Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles few-shot learning across different domains. It aims at transferring prior knowledge learned on the source dataset to novel target datasets. The CD-FSL task is especially challenged by the huge domain gap between different datasets. Critically, such a domain gap actually comes from the changes of visual styles, and wave-SAN empirically shows that spanning the style distribution of the source data helps alleviate this issue. However, wave-SAN simply swaps styles of two images. Such a vanilla operation makes the generated styles ``real'' and ``easy'', which still fall into the original set of the source styles. Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL. Particularly, our style attack method synthesizes both ``virtual'' and ``hard'' adversarial styles for model training. This is achieved by perturbing the original style with the signed style gradients. By continually attacking styles and forcing the model to recognize these challenging adversarial styles, our model is gradually robust to the visual styles, thus boosting the generalization ability for novel target datasets. Besides the typical CNN-based backbone, we also employ our StyleAdv method on large-scale pretrained vision transformer. Extensive experiments conducted on eight various target datasets show the effectiveness of our method. Whether built upon ResNet or ViT, we achieve the new state of the art for CD-FSL. Code is available at https://github.com/lovelyqian/StyleAdv-CDFSL.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 57 of its 76 references that are in the map. First posted on arXiv 18 Feb 2023.

Builds on

57 of 76 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  10. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  11. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  12. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
38 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  3. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  4. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  5. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  7. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  8. 2017One pixel attack for fooling deep neural networkscited by 579
  9. 2021Domain Generalization with MixStylecited by 563
  10. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  11. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  12. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  13. 2019Adversarial Examples Improve Image Recognitioncited by 283
  14. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  15. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
  16. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  17. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  18. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  19. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  20. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
  21. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  22. 2019Functional Adversarial Attackscited by 82
  23. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  24. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  25. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  26. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  27. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  28. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  29. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  30. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  31. 2019ProtoGAN: Towards Few Shot Learning for Action Recognitioncited by 41
  32. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  33. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  34. 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
  35. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  36. 2022MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentationcited by 27
  37. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  38. 2020Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classificationcited by 20

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 13; 2025: 21; 2026: 15.

53 papers.

Sort:

By area:

  1. 2023DePT: Decoupled Prompt Tuningcited by 58
  2. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  3. 2025Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detectioncited by 24
  4. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
  5. 2025EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answeringcited by 19
  6. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  7. 2025EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmarkcited by 16
  8. 2023Simple Semantic-Aided Few-Shot Learningcited by 15
  9. 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detectioncited by 14
  10. 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptationcited by 14
  11. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  12. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
38 more
  1. 2025EarthSynth: Generating Informative Earth Observation with Diffusion Modelscited by 12
  2. 2023On the Importance of Spatial Relations for Few-shot Action Recognitioncited by 11
  3. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  4. 2024Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselvescited by 10
  5. 2025Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learningcited by 9
  6. 2024Cross-Domain Few-Shot Learning via Adaptive Transformer Networkscited by 7
  7. 2025A Closer Look at Conditional Prompt Tuning for Vision-Language Modelscited by 7
  8. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  9. 2024StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalizationcited by 5
  10. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  11. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  12. 2024Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Modelscited by 5
  13. 2026Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learningcited by 5
  14. 2024Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanismscited by 4
  15. 2026Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learningcited by 4
  16. 2026Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignmentcited by 4
  17. 2024SETA: Semantic-Aware Token Augmentation for Domain Generalizationcited by 3
  18. 2025Few-Shot Vision-Language Action-Incremental Policy Learningcited by 3
  19. 2024Cross-Modal Few-Shot Learning: a Generative Transfer Learning Frameworkcited by 2
  20. 2025Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservationcited by 2
  21. 2026DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learningcited by 2
  22. 2025UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesiscited by 1
  23. 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detectioncited by 1
  24. 2025Enhancing Environmental Robustness in Few-shot Learning via Conditional Representation Learningcited by 0
  25. 2025Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichmentcited by 0
  26. 2025Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examplescited by 0
  27. 2025MetaLab: Few-Shot Game Changer for Image Recognitioncited by 0
  28. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  29. 2025Provably Robust Adaptation for Language-Empowered Foundation Modelscited by 0
  30. 2025Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labelscited by 0
  31. 2025FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learningcited by 0
  32. 2026IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learningcited by 0
  33. 2026PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learningcited by 0
  34. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0
  35. 2026SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learningcited by 0
  36. 2026GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detectioncited by 0
  37. 2026The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answeringcited by 0
  38. 2026When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learningcited by 0

50 most cited of 53 All 53 (JSON)