mlsanityData to 14 Oct 2026

Recent Advances in Open Set Recognition: A Survey

arXiv 1811.08581 ↗First posted 21 Nov 2018cs.LG stat.MLcited by 310

Not on the map. Why?

Abstract (arXiv)

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with the unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also overview the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.

Key facts. Cited by 310 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 51; 2022: 59; 2023: 59; 2024: 60; 2025: 42; 2026: 38.

310 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  2. 2021Domain Generalization: A Surveycited by 764
  3. 2022Language-driven Semantic Segmentationcited by 717
  4. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  5. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  6. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  7. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  8. 2021Open-World Semi-Supervised Learningcited by 165
  9. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  10. 2022A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learningcited by 154
  11. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  12. 2021Learning Placeholders for Open-Set Recognitioncited by 121
38 more
  1. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  2. 2021Evidential Deep Learning for Open Set Action Recognitioncited by 96
  3. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 93
  4. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  5. 2022PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discoverycited by 87
  6. 2022A Theoretical Study on Solving Continual Learningcited by 80
  7. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  8. 2023Federated Learning for Medical Image Analysis: A Surveycited by 78
  9. 2024Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directionscited by 77
  10. 2022Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embeddingcited by 67
  11. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 61
  12. 2022Open-environment Machine Learningcited by 48
  13. 2024Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusioncited by 47
  14. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
  15. 2022The Met Dataset: Instance-level Recognition for Artworkscited by 40
  16. 2022Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Modelscited by 40
  17. 2022Novel Class Discovery without Forgettingcited by 39
  18. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  19. 2021Open-world Machine Learning: Applications, Challenges, and Opportunitiescited by 34
  20. 2022Active Learning for Open-set Annotationcited by 34
  21. 2023On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansioncited by 34
  22. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  23. 2022Grow and Merge: A Unified Framework for Continuous Categories Discoverycited by 33
  24. 2022LidarCLIP or: How I Learned to Talk to Point Cloudscited by 33
  25. 2023Continuous Learning for Android Malware Detectioncited by 33
  26. 2024Active Generalized Category Discoverycited by 31
  27. 2021Few-shot Open-set Recognition by Transformation Consistencycited by 29
  28. 2021Valid prediction intervals for regression problemscited by 29
  29. 2023Domain Generalization in Computational Pathology: Survey and Guidelinescited by 29
  30. 2022Class-Specific Semantic Reconstruction for Open Set Recognitioncited by 28
  31. 2021Learning Bounds for Open-Set Learningcited by 27
  32. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  33. 2022Towards Open Set Video Anomaly Detectioncited by 26
  34. 2023Open Set Action Recognition via Multi-Label Evidential Learningcited by 26
  35. 2021Segmentation-grounded Scene Graph Generationcited by 25
  36. 2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 25
  37. 2023Incremental Generalized Category Discoverycited by 25
  38. 2023Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalizationcited by 24

50 most cited of 310 All 310 (JSON)