mlsanityData to 14 Oct 2026

Cross-Domain Few-Shot Learning via Adaptive Transformer Networks

arXiv 2401.13987 ↗First posted 25 Jan 2024cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive transformer network (ADAPTER), a simple but effective solution for cross-domain few-shot learning where there exist large domain shifts between the base task and the target task. ADAPTER is built upon the idea of bidirectional cross-attention to learn transferable features between the two domains. The proposed architecture is trained with DINO to produce diverse, and less biased features to avoid the supervision collapse problem. Furthermore, the label smoothing approach is proposed to improve the consistency and reliability of the predictions by also considering the predicted labels of the close samples in the embedding space. The performance of ADAPTER is rigorously evaluated in the BSCD-FSL benchmarks in which it outperforms prior arts with significant margins.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 32 of its 37 references that are in the map. First posted on arXiv 25 Jan 2024.

Builds on

32 of 37 references.

References · 32

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  11. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  12. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
20 more
  1. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  2. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  3. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 264
  4. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 219
  5. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  6. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  7. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  8. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  9. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  10. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 76
  11. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  12. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  13. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  14. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 50
  15. 2019Open Set Domain Adaptation: Theoretical Bound and Algorithmcited by 48
  16. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
  17. 2023Dual Adaptive Representation Alignment for Cross-domain Few-shot Learningcited by 15
  18. 2022Domain Adaptation via Bidirectional Cross-Attention Transformercited by 13
  19. 2019A Broader Study of Cross-Domain Few-Shot Learningcited by 10
  20. 2020Improving the Backpropagation Algorithm with Consequentialism Weight Updates over Mini-Batchescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2025CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language Modelscited by 6
  2. 2024Few-Shot Class Incremental Learning via Robust Transformer Approachcited by 4
  3. 2025Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservationcited by 2
  4. 2026FreeGNN: Continual Source-Free Graph Neural Network Adaptation for Renewable Energy Forecastingcited by 1
  5. 2025A Cross-Domain Few-Shot Learning Method Based on Domain Knowledge Mappingcited by 0
  6. 2026ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarioscited by 0
  7. 2026Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Modelcited by 0