mlsanityData to 7 Oct 2026

Few-Shot Open-Set Recognition using Meta-Learning

arXiv 2005.13713 ↗First posted 27 May 2020cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

The problem of open-set recognition is considered. While previous approaches only consider this problem in the context of large-scale classifier training, we seek a unified solution for this and the low-shot classification setting. It is argued that the classic softmax classifier is a poor solution for open-set recognition, since it tends to overfit on the training classes. Randomization is then proposed as a solution to this problem. This suggests the use of meta-learning techniques, commonly used for few-shot classification, for the solution of open-set recognition. A new oPen sEt mEta LEaRning (PEELER) algorithm is then introduced. This combines the random selection of a set of novel classes per episode, a loss that maximizes the posterior entropy for examples of those classes, and a new metric learning formulation based on the Mahalanobis distance. Experimental results show that PEELER achieves state of the art open set recognition performance for both few-shot and large-scale recognition. On CIFAR and miniImageNet, it achieves substantial gains in seen/unseen class detection AUROC for a given seen-class classification accuracy.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 14; 2024: 9; 2025: 8; 2026: 3.

50 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022Language-driven Semantic Segmentationcited by 711
  3. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  4. 2021Few-shot Open-set Recognition by Transformation Consistencycited by 29
  5. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  6. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  7. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  8. 2023Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worldscited by 11
  9. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  10. 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
  11. 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognitioncited by 10
  12. 2023Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systemscited by 9
38 more
  1. 2021Bayesian Embeddings for Few-Shot Open World Recognitioncited by 8
  2. 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
  3. 2022Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spottingcited by 7
  4. 2023A Survey on Open-Set Image Recognitioncited by 7
  5. 2022Few-shot Open-set Recognition Using Background as Unknownscited by 6
  6. 2023Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorancecited by 6
  7. 2024Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognitioncited by 6
  8. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  9. 2023Domain Adaptive Few-Shot Open-Set Learningcited by 4
  10. 2021Reconstruction guided Meta-learning for Few Shot Open Set Recognitioncited by 3
  11. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  12. 2024Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundarycited by 3
  13. 2022Model-Agnostic Few-Shot Open-Set Recognitioncited by 2
  14. 2023Learning from Pixels with Expert Observationscited by 2
  15. 2024EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logitscited by 2
  16. 2025Hyperbolic Dual Feature Augmentation for Open-Environmentcited by 2
  17. 2025Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentationcited by 2
  18. 2021One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classificationcited by 1
  19. 2023A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attributioncited by 1
  20. 2023A Metalearned Neural Circuit for Nonparametric Bayesian Inferencecited by 1
  21. 2023Advancing Image Retrieval with Few-Shot Learning and Relevance Feedbackcited by 1
  22. 2024LLM meets Vision-Language Models for Zero-Shot One-Class Classificationcited by 1
  23. 2025Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancementcited by 1
  24. 2021External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagerycited by 0
  25. 2022Persian Natural Language Inference: A Meta-learning approachcited by 0
  26. 2022SIAD: Self-supervised Image Anomaly Detection Systemcited by 0
  27. 2023Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examplescited by 0
  28. 2024Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognitioncited by 0
  29. 2024Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margincited by 0
  30. 2024Unlocking Transfer Learning for Open-World Few-Shot Recognitioncited by 0
  31. 2025MetaXCR: Reinforcement-Based Meta-Transfer Learning for Cross-Lingual Commonsense Reasoningcited by 0
  32. 2025A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domainscited by 0
  33. 2025Few-shot Novel Category Discoverycited by 0
  34. 2025Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learningcited by 0
  35. 2025Few-shot Unknown Class Discovery of Hyperspectral Images with Prototype Learning and Clusteringcited by 0
  36. 2026A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discriminationcited by 0
  37. 2026Visual Product Search Benchmarkcited by 0
  38. 2026A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalizationcited by 0