mlsanityData to 14 Oct 2026

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

arXiv 2207.07826 ↗First posted 16 Jul 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Few-shot learning (FSL) aims to recognize novel queries with only a few support samples through leveraging prior knowledge from a base dataset. In this paper, we consider the domain shift problem in FSL and aim to address the domain gap between the support set and the query set. Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class. To this end, we propose a novel approach, namely stabPA, to learn prototypical compact and cross-domain aligned representations, so that the domain shift and few-shot learning can be addressed simultaneously. We evaluate our approach on two new CDCS-FSL benchmarks built from the DomainNet and Office-Home datasets respectively. Remarkably, our approach outperforms multiple elaborated baselines by a large margin, e.g., improving 5-shot accuracy by 6.0 points on average on DomainNet. Code is available at https://github.com/WentaoChen0813/CDCS-FSL

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 16 Jul 2022.

Builds on

36 of 53 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  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. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2016Matching Networks for One Shot Learningcited by 2,255
  10. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  11. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  12. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
24 more
  1. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  2. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  3. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  4. 2019A Closer Look at Few-shot Classificationcited by 684
  5. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  8. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  9. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  10. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  11. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  12. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  13. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  14. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  15. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  16. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  17. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  18. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 76
  19. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  20. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  21. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  22. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 50
  23. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  24. 2021Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Imagescited by 8

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1; 2025: 1.

5 papers.

  1. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  2. 2023Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillationcited by 7
  3. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  4. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  5. 2025A Cross-Domain Few-Shot Learning Method Based on Domain Knowledge Mappingcited by 0