mlsanityData to 7 Oct 2026

Generalizing from a Few Examples: A Survey on Few-Shot Learning

arXiv 1904.05046 ↗First posted 10 Apr 2019cs.LG cs.AIcited by 462

Not on the map. Why?

Abstract (arXiv)

Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small. Recently, Few-Shot Learning (FSL) is proposed to tackle this problem. Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this paper, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimized is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience; (ii) model, which uses prior knowledge to reduce the size of the hypothesis space; and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications and theories, are also proposed to provide insights for future research.

Key facts. Cited by 462 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 115; 2022: 135; 2023: 130; 2024: 50; 2025: 27; 2026: 5.

462 papers.

Sort:

By area:

  1. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  2. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  3. 2021Deep Long-Tailed Learning: A Surveycited by 416
  4. 2023Large Language Models in Finance: A Surveycited by 223
  5. 2021A Survey of Human-in-the-loop for Machine Learningcited by 214
  6. 2021Trustworthy AI: From Principles to Practicescited by 206
  7. 2023Don't Make Your LLM an Evaluation Benchmark Cheatercited by 194
  8. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  9. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 143
  10. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  11. 2021Graph Neural Networks in Network Neurosciencecited by 91
  12. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
38 more
  1. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  2. 2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
  3. 2023CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representationscited by 67
  4. 2022Reliable extrapolation of deep neural operators informed by physics or sparse observationscited by 62
  5. 2021Continual Learning via Local Module Compositioncited by 61
  6. 2024Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMscited by 61
  7. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  8. 2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
  9. 2022Mixed Differential Privacy in Computer Visioncited by 53
  10. 2022NatGen: Generative pre-training by "Naturalizing" source codecited by 53
  11. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  12. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  13. 2023Advances in Deep Concealed Scene Understandingcited by 47
  14. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 44
  15. 2022Modeling Image Composition for Complex Scene Generationcited by 43
  16. 2024PoCo: Policy Composition from and for Heterogeneous Robot Learningcited by 42
  17. 2021Multi-Objective Meta Learningcited by 39
  18. 2021A Survey on Neural-symbolic Learning Systemscited by 39
  19. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  20. 2025BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster responsecited by 39
  21. 2022Breaking Bad: A Dataset for Geometric Fracture and Reassemblycited by 38
  22. 2021The Threat of Offensive AI to Organizationscited by 37
  23. 2021Hierarchical Few-Shot Imitation with Skill Transition Modelscited by 37
  24. 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
  25. 2022Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Reviewcited by 37
  26. 2021Chemical-Reaction-Aware Molecule Representation Learningcited by 36
  27. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  28. 2021Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directionscited by 35
  29. 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
  30. 2023Large Language Models Are Zero-Shot Text Classifierscited by 35
  31. 2022Sketch3T: Test-Time Training for Zero-Shot SBIRcited by 34
  32. 2022DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualizationcited by 32
  33. 2021Multi-fidelity regression using artificial neural networks: efficient approximation of parameter-dependent output quantitiescited by 31
  34. 2021The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactionscited by 31
  35. 2022Unlearning Graph Classifiers with Limited Data Resourcescited by 31
  36. 2024Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuningcited by 31
  37. 2021Meta Discovery: Learning to Discover Novel Classes given Very Limited Datacited by 30
  38. 2021A Systematic Collection of Medical Image Datasets for Deep Learningcited by 29

50 most cited of 462 All 462 (JSON)