mlsanityData to 7 Oct 2026

SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learning

arXiv 2603.05135 ↗First posted 5 Mar 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Cross-Domain Few-Shot Learning (CD-FSL) aims to transfer knowledge from a seen source domain to unseen target domains, serving as a key benchmark for evaluating the robustness and transferability of models. Existing style-based perturbation methods mitigate domain shift but often suffer from gradient instability and convergence to sharp minima.To address these limitations, we propose a novel crop-global style perturbation network, termed Self-Reorientation Adversarial underlineStyle underlinePerturbation (SRasP). Specifically, SRasP leverages global semantic guidance to identify incoherent crops, followed by reorienting and aggregating the style gradients of these crops with the global style gradients within one image. Furthermore, we propose a novel multi-objective optimization function to maximize visual discrepancy while enforcing semantic consistency among global, crop, and adversarial features. Applying the stabilized perturbations during training encourages convergence toward flatter and more transferable solutions, improving generalization to unseen domains. Extensive experiments are conducted on multiple CD-FSL benchmarks, demonstrating consistent improvements over state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 61 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

42 of 61 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  6. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  7. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  8. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  9. 2021Domain Generalization with MixStylecited by 563
  10. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  11. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  12. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
30 more
  1. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  2. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  3. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
  4. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  5. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  6. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  7. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  8. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  9. 2020On Episodes, Prototypical Networks, and Few-shot Learningcited by 46
  10. 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
  11. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  12. 2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
  13. 2022TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learningcited by 16
  14. 2024WAVE: Weight Templates for Adaptive Initialization of Variable-sized Modelscited by 16
  15. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  16. 2023Dual Adaptive Representation Alignment for Cross-domain Few-shot Learningcited by 15
  17. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  18. 2024Transferring Core Knowledge via Learngenescited by 10
  19. 2023Genes in Intelligent Agentscited by 9
  20. 2024Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learningcited by 9
  21. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  22. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  23. 2024SVasP: Self-Versatility Adversarial Style Perturbation for Cross-Domain Few-Shot Learningcited by 5
  24. 2023SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learningcited by 4
  25. 2023Clustered-patch Element Connection for Few-shot Learningcited by 4
  26. 2025Random Registers for Cross-Domain Few-Shot Learningcited by 4
  27. 2023Randomized Adversarial Style Perturbations for Domain Generalizationcited by 3
  28. 2023Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learningcited by 3
  29. 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learningcited by 3
  30. 2024Task-Specific Preconditioner for Cross-Domain Few-Shot Learningcited by 1

Built on by

Not cited yet.