mlsanityData to 7 Oct 2026

A Theoretical Analysis of the Number of Shots in Few-Shot Learning

arXiv 1909.11722 ↗First posted 25 Sep 2019cs.LG stat.MLcited by 39

Not on the map. Why?

Abstract (arXiv)

Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks during meta-training to quickly adapt to new tasks during meta-testing. In this formulation, the number of shots exploited during meta-training has an impact on the recognition performance at meta-test time. Generally, the shot number used in meta-training should match the one used in meta-testing to obtain the best performance. We introduce a theoretical analysis of the impact of the shot number on Prototypical Networks, a state-of-the-art few-shot classification method. From our analysis, we propose a simple method that is robust to the choice of shot number used during meta-training, which is a crucial hyperparameter. The performance of our model trained for an arbitrary meta-training shot number shows great performance for different values of meta-testing shot numbers. We experimentally demonstrate our approach on different few-shot classification benchmarks.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 13; 2023: 7; 2024: 7; 2025: 2.

39 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  3. 2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
  4. 2023Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoningcited by 49
  5. 2024LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planningcited by 44
  6. 2021Few-Shot Learning with Class Imbalancecited by 18
  7. 2023Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentationcited by 17
  8. 2021Few-Shot Learning with a Strong Teachercited by 16
  9. 2021A Closer Look at Prototype Classifier for Few-shot Image Classificationcited by 15
  10. 2023ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusioncited by 15
  11. 2024How Can I Get It Right? Using GPT to Rephrase Incorrect Trainee Responsescited by 12
  12. 2022Few-Shot Learning on Graphscited by 11
27 more
  1. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  2. 2021Feature Generation for Long-tail Classificationcited by 9
  3. 2021Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotatorcited by 8
  4. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  5. 2022Temporal Transductive Inference for Few-Shot Video Object Segmentationcited by 6
  6. 2022Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptilecited by 6
  7. 2021MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Taggingcited by 4
  8. 2024Enhanced Multimodal Content Moderation of Children's Videos using Audiovisual Fusioncited by 4
  9. 2023Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challengescited by 3
  10. 2023Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizercited by 3
  11. 2021MetaKernel: Learning Variational Random Features with Limited Labelscited by 2
  12. 2022Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generationcited by 2
  13. 2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
  14. 2024Approximation Rates and VC-Dimension Bounds for (P)ReLU MLP Mixture of Expertscited by 2
  15. 2021Mutual-Information Based Few-Shot Classificationcited by 1
  16. 2021Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learningcited by 1
  17. 2022Increasing Model Generalizability for Unsupervised Domain Adaptationcited by 1
  18. 2022Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learningcited by 1
  19. 2023P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classificationcited by 1
  20. 2024Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applicationscited by 1
  21. 2025Efficient Detection of Intermittent Job Failures Using Few-Shot Learningcited by 1
  22. 2025CCoMAML: Efficient Cattle Identification Using Cooperative Model-Agnostic Meta-Learningcited by 1
  23. 2022Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learnerscited by 0
  24. 2022Constrained Few-Shot Learning: Human-Like Low Sample Complexity Learning and Non-Episodic Text Classificationcited by 0
  25. 2022A Study on Representation Transfer for Few-Shot Learningcited by 0
  26. 2024Unsupervised Domain Adaptation Using Compact Internal Representationscited by 0
  27. 2024EnvId: A Metric Learning Approach for Forensic Few-Shot Identification of Unseen Environmentscited by 0