mlsanityData to 7 Oct 2026

Boosting Few-Shot Visual Learning with Self-Supervision

arXiv 1906.05186 ↗First posted 12 Jun 2019cs.CV cs.LGcited by 140

Not on the map. Why?

Abstract (arXiv)

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learning focuses instead on unlabeled data and looks into it for the supervisory signal to feed high capacity deep neural networks. In this work we exploit the complementarity of these two domains and propose an approach for improving few-shot learning through self-supervision. We use self-supervision as an auxiliary task in a few-shot learning pipeline, enabling feature extractors to learn richer and more transferable visual representations while still using few annotated samples. Through self-supervision, our approach can be naturally extended towards using diverse unlabeled data from other datasets in the few-shot setting. We report consistent improvements across an array of architectures, datasets and self-supervision techniques.

Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 55; 2022: 39; 2023: 22; 2024: 16; 2025: 7; 2026: 1.

140 papers.

Sort:

By area:

  1. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  2. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  3. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  4. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  5. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
  6. 2021Relational Embedding for Few-Shot Classificationcited by 74
  7. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  8. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  9. 2021Equivariant Contrastive Learningcited by 65
  10. 2021Few-Shot Lifelong Learningcited by 58
  11. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 57
  12. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
38 more
  1. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  2. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  3. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  4. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  5. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  6. 2022Few-Shot Classification with Contrastive Learningcited by 31
  7. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  8. 2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
  9. 2023MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognitioncited by 26
  10. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  11. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  12. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  13. 2023Supervised Masked Knowledge Distillation for Few-Shot Transformerscited by 23
  14. 2023S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learningcited by 23
  15. 2021LibFewShot: A Comprehensive Library for Few-shot Learningcited by 21
  16. 2023MaskCon: Masked Contrastive Learning for Coarse-Labelled Datasetcited by 21
  17. 2023Context-Aware Meta-Learningcited by 20
  18. 2021A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learningcited by 19
  19. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
  20. 2022Few-shot Relational Reasoning via Connection Subgraph Pretrainingcited by 18
  21. 2024Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planescited by 17
  22. 2021Few-Shot Learning with a Strong Teachercited by 16
  23. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  24. 2021Rich Semantics Improve Few-shot Learningcited by 15
  25. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
  26. 2023Simple Semantic-Aided Few-Shot Learningcited by 15
  27. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  28. 2022Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learningcited by 14
  29. 2022Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregationcited by 14
  30. 2021Few-Shot and Continual Learning with Attentive Independent Mechanismscited by 13
  31. 2022Continual Learning with Evolving Class Ontologiescited by 13
  32. 2023Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurringcited by 13
  33. 2022Multi-level Second-order Few-shot Learningcited by 12
  34. 2021Boosting Few-Shot Classification with View-Learnable Contrastive Learningcited by 11
  35. 2021Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptationcited by 11
  36. 2021Semi-Supervised Learning with Taxonomic Labelscited by 11
  37. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  38. 2021Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Imagescited by 8

50 most cited of 140 All 140 (JSON)