mlsanityData to 7 Oct 2026

Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning

arXiv 2511.14279 ↗First posted 18 Nov 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Cross-Domain Few-Shot Learning (CDFSL) endeavors to transfer generalized knowledge from the source domain to target domains using only a minimal amount of training data, which faces a triplet of learning challenges in the meantime, i.e., semantic disjoint, large domain discrepancy, and data scarcity. Different from predominant CDFSL works focused on generalized representations, we make novel attempts to construct Intermediate Domain Proxies (IDP) with source feature embeddings as the codebook and reconstruct the target domain feature with this learned codebook. We then conduct an empirical study to explore the intrinsic attributes from perspectives of visual styles and semantic contents in intermediate domain proxies. Reaping benefits from these attributes of intermediate domains, we develop a fast domain alignment method to use these proxies as learning guidance for target domain feature transformation. With the collaborative learning of intermediate domain reconstruction and target feature transformation, our proposed model is able to surpass the state-of-the-art models by a margin on 8 cross-domain few-shot learning benchmarks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 84 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

43 of 84 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  8. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  11. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  12. 2019A Closer Look at Few-shot Classificationcited by 679
31 more
  1. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  2. 2015A Neural Algorithm of Artistic Stylecited by 480
  3. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 459
  4. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  5. 2018Meta-learning with differentiable closed-form solverscited by 395
  6. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  7. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  8. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  9. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  10. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  11. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  12. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  13. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  14. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  15. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  16. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  17. 2021Model-Based Domain Generalizationcited by 103
  18. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  19. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  20. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  21. 2020Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosiscited by 60
  22. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  23. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  24. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  25. 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
  26. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  27. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  28. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  29. 2020Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classificationcited by 20
  30. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  31. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1
  2. 2026Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generationcited by 1