mlsanityData to 7 Oct 2026

Self-training for Few-shot Transfer Across Extreme Task Differences

arXiv 2010.07734 ↗First posted 15 Oct 2020cs.CV cs.AI cs.LGcited by 75

Not on the map. Why?

Abstract (arXiv)

Most few-shot learning techniques are pre-trained on a large, labeled "base dataset". In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training in a different "source" problem domain (e.g., ImageNet), which can be very different from the desired target task. Traditional few-shot and transfer learning techniques fail in the presence of such extreme differences between the source and target tasks. In this paper, we present a simple and effective solution to tackle this extreme domain gap: self-training a source domain representation on unlabeled data from the target domain. We show that this improves one-shot performance on the target domain by 2.9 points on average on the challenging BSCD-FSL benchmark consisting of datasets from multiple domains. Our code is available at https://github.com/cpphoo/STARTUP.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 22; 2023: 15; 2024: 16; 2025: 7; 2026: 2.

75 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  3. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  4. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  5. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  6. 2022Learning to Detect Mobile Objects from LiDAR Scans Without Labelscited by 44
  7. 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
  8. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  9. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  10. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
  11. 2023Context-Aware Meta-Learningcited by 20
  12. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
38 more
  1. 2022CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detectioncited by 17
  2. 2021Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmarkcited by 16
  3. 2022TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learningcited by 16
  4. 2021A Closer Look at Prototype Classifier for Few-shot Image Classificationcited by 15
  5. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
  6. 2023Dual Adaptive Representation Alignment for Cross-domain Few-shot Learningcited by 15
  7. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  8. 2021Hierarchical Variational Memory for Few-shot Learning Across Domainscited by 14
  9. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  10. 2024Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognitioncited by 14
  11. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
  12. 2024Layout Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)cited by 13
  13. 2023CDFSL-V: Cross-Domain Few-Shot Learning for Videoscited by 12
  14. 2024Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Promptingcited by 10
  15. 2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learningcited by 9
  16. 2023Cross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognitioncited by 9
  17. 2024Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Promptingcited by 9
  18. 2021On the Importance of Firth Bias Reduction in Few-Shot Classificationcited by 7
  19. 2024Cross-Domain Few-Shot Learning via Adaptive Transformer Networkscited by 7
  20. 2021Unsupervised Finetuningcited by 6
  21. 2022ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learningcited by 6
  22. 2022How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentationcited by 6
  23. 2023Simulated Annealing in Early Layers Leads to Better Generalizationcited by 6
  24. 2023Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillationcited by 6
  25. 2024SynFER: Towards Boosting Facial Expression Recognition with Synthetic Datacited by 6
  26. 2022Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representationscited by 5
  27. 2022Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognitioncited by 5
  28. 2022Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyondcited by 5
  29. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  30. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  31. 2022Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognitioncited by 4
  32. 2022Cross-Domain Few-Shot Classification via Inter-Source Stylizationcited by 4
  33. 2023Distilling from Similar Tasks for Transfer Learning on a Budgetcited by 4
  34. 2023Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classificationcited by 4
  35. 2024Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognitioncited by 4
  36. 2024Better Monocular 3D Detectors with LiDAR from the Pastcited by 4
  37. 2026Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignmentcited by 4
  38. 2021Streaming Self-Training via Domain-Agnostic Unlabeled Imagescited by 3

50 most cited of 75 All 75 (JSON)