mlsanityData to 14 Oct 2026

Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning

arXiv 2506.03110 ↗First posted 3 Jun 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Vision Transformer (ViT) has achieved remarkable success due to its large-scale pretraining on general domains, but it still faces challenges when applying it to downstream distant domains that have only scarce training data, which gives rise to the Cross-Domain Few-Shot Learning (CDFSL) task. Inspired by Self-Attention's insensitivity to token orders, we find an interesting phenomenon neglected in current works: disrupting the continuity of image tokens (i.e., making pixels not smoothly transited across patches) in ViT leads to a noticeable performance decline in the general (source) domain but only a marginal decrease in downstream target domains. This questions the role of image tokens' continuity in ViT's generalization under large domain gaps. In this paper, we delve into this phenomenon for an interpretation. We find continuity aids ViT in learning larger spatial patterns, which are harder to transfer than smaller ones, enlarging domain distances. Meanwhile, it implies that only smaller patterns within each patch could be transferred under extreme domain gaps. Based on this interpretation, we further propose a simple yet effective method for CDFSL that better disrupts the continuity of image tokens, encouraging the model to rely less on large patterns and more on smaller ones. Extensive experiments show the effectiveness of our method in reducing domain gaps and outperforming state-of-the-art works. Codes and models are available at https://github.com/shuaiyi308/ReCIT.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

34 of 44 references.

References · 34

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  6. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  7. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  8. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  9. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  10. 2021Intriguing Properties of Vision Transformerscited by 446
  11. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  12. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
22 more
  1. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 234
  2. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 219
  3. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  4. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  5. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  6. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  7. 2022Reliability of CKA as a Similarity Measure in Deep Learningcited by 87
  8. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 76
  9. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 71
  10. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  11. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  12. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  13. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  14. 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
  15. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  16. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  17. 2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
  18. 2024Compositional Few-Shot Class-Incremental Learningcited by 18
  19. 2022Accumulated Trivial Attention Matters in Vision Transformers on Small Datasetscited by 15
  20. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
  21. 2024Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learningcited by 9
  22. 2023ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learningcited by 1
  2. 2026SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learningcited by 0
  3. 2026When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learningcited by 0