mlsanityData to 7 Oct 2026

Cross-Domain Few-Shot Classification via Inter-Source Stylization

arXiv 2208.08015 ↗First posted 17 Aug 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The goal of Cross-Domain Few-Shot Classification (CDFSC) is to accurately classify a target dataset with limited labelled data by exploiting the knowledge of a richly labelled auxiliary dataset, despite the differences between the domains of the two datasets. Some existing approaches require labelled samples from multiple domains for model training. However, these methods fail when the sample labels are scarce. To overcome this challenge, this paper proposes a solution that makes use of multiple source domains without the need for additional labeling costs. Specifically, one of the source domains is completely tagged, while the others are untagged. An Inter-Source Stylization Network (ISSNet) is then introduced to enhance stylisation across multiple source domains, enriching data distribution and model's generalization capabilities. Experiments on 8 target datasets show that ISSNet leverages unlabelled data from multiple source data and significantly reduces the negative impact of domain gaps on classification performance compared to several baseline methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 53 of its 80 references that are in the map. First posted on arXiv 17 Aug 2022.

Builds on

53 of 80 references.

References · 53

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2016Matching Networks for One Shot Learningcited by 2,246
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  6. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  7. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  9. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  10. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  11. 2019A Closer Look at Few-shot Classificationcited by 679
  12. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
38 more
  1. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  2. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  3. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  4. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  5. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  6. 2020A Brief Review of Domain Adaptationcited by 287
  7. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  8. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  9. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
  10. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  11. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  12. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  13. 2021Generalized Source-free Domain Adaptationcited by 175
  14. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  15. 2018Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shiftcited by 109
  16. 2020Semantic Segmentation of Underwater Imagery: Dataset and Benchmarkcited by 95
  17. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  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. 2020Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptationcited by 64
  21. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  22. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  23. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  24. 2020Curriculum Manager for Source Selection in Multi-Source Domain Adaptationcited by 55
  25. 2020Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptationcited by 53
  26. 2021Dynamic Weighted Learning for Unsupervised Domain Adaptationcited by 53
  27. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  28. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  29. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  30. 2020Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Surveycited by 47
  31. 2019TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learningcited by 39
  32. 2021CrossNorm and SelfNorm for Generalization under Distribution Shiftscited by 33
  33. 2020Cross-Domain Few-Shot Learning by Representation Fusioncited by 32
  34. 2021Unsupervised Multi-Source Domain Adaptation for Person Re-Identificationcited by 30
  35. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  36. 2018Feature Space Transfer for Data Augmentationcited by 21
  37. 2020Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classificationcited by 20
  38. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  2. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
  3. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  4. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3