mlsanityData to 7 Oct 2026

A Survey on Open Set Recognition

arXiv 2109.00893 ↗First posted 18 Aug 2021cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Open Set Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In this paper, we provide a survey of existing works about OSR and distinguish their respective advantages and disadvantages to help out new researchers interested in the subject. The categorization of OSR models is provided along with an extensive summary of recent progress. Additionally, the relationships between OSR and its related tasks including multi-class classification and novelty detection are analyzed. It is concluded that OSR can appropriately deal with unknown instances in the real-world where capturing all possible classes in the training data is not practical. Lastly, applications of OSR are highlighted and some new directions for future research topics are suggested.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 55 of its 177 references that are in the map. First posted on arXiv 18 Aug 2021.

Builds on

55 of 177 references.

References · 55

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  8. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  9. 2017Selective Classification for Deep Neural Networkscited by 799
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  11. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  12. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
38 more
  1. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  2. 2015Towards Open Set Deep Networkscited by 533
  3. 2018A Survey on Deep Transfer Learningcited by 417
  4. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  5. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  6. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  7. 2017Detecting Adversarial Samples from Artifactscited by 244
  8. 2014Towards Open World Recognitioncited by 226
  9. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  10. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  11. 2018Reducing Network Agnostophobiacited by 165
  12. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  13. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  14. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  15. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  16. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  17. 2017Domain Adaptation for Visual Applications: A Comprehensive Surveycited by 127
  18. 2017DOC: Deep Open Classification of Text Documentscited by 109
  19. 2015A Deeper Look at Dataset Biascited by 86
  20. 2015The Extreme Value Machinecited by 78
  21. 2018Learning Deep Features for One-Class Classificationcited by 76
  22. 2018Towards Open-Set Identity Preserving Face Synthesiscited by 74
  23. 2017Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reductioncited by 49
  24. 2018Learning a Neural-network-based Representation for Open Set Recognitioncited by 40
  25. 2017Unbounded cache model for online language modeling with open vocabularycited by 37
  26. 2017Sparse Representation-based Open Set Recognitioncited by 36
  27. 2017Toward Open-Set Face Recognitioncited by 29
  28. 2017Failing to Learn: Autonomously Identifying Perception Failures for Self-driving Carscited by 28
  29. 2017Recent Advances in Zero-shot Recognitioncited by 28
  30. 2017Robust, Deep and Inductive Anomaly Detectioncited by 24
  31. 2017Open-Category Classification by Adversarial Sample Generationcited by 24
  32. 2018Unseen Class Discovery in Open-world Classificationcited by 20
  33. 2017Provable Self-Representation Based Outlier Detection in a Union of Subspacescited by 18
  34. 2017Unconstrained Face Detection and Open-Set Face Recognition Challengecited by 18
  35. 2015Place Categorization and Semantic Mapping on a Mobile Robotcited by 12
  36. 2019Deep CNN-based Multi-task Learning for Open-Set Recognitioncited by 12
  37. 2018Open Vocabulary Learning on Source Code with a Graph-Structured Cachecited by 10
  38. 2016A Survey of Stealth Malware: Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutionscited by 8

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 7; 2024: 9; 2025: 2; 2026: 3.

25 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  3. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  4. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  5. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  6. 2024Anomaly Detection Based on Isolation Mechanisms: A Surveycited by 10
  7. 2023Calibrated Out-of-Distribution Detection with a Generic Representationcited by 8
  8. 2024AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systemscited by 7
  9. 2022Confident AIcited by 6
  10. 2023Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalizationcited by 6
  11. 2024Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Surveycited by 6
  12. 2023Managing the unknown: a survey on Open Set Recognition and tangential areascited by 4
13 more
  1. 2024Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networkscited by 4
  2. 2023Expecting The Unexpected: Towards Broad Out-Of-Distribution Detectioncited by 3
  3. 2023Open-Set Multivariate Time-Series Anomaly Detectioncited by 3
  4. 2021Unsupervised detection and open-set classification of fast-ramped flexibility activation eventscited by 2
  5. 2023torchosr -- a PyTorch extension package for Open Set Recognition models evaluation in Pythoncited by 2
  6. 2024Comparison of Embedded Spaces for Deep Learning Classificationcited by 1
  7. 2024Resilience to the Flowing Unknown: an Open Set Recognition Framework for Data Streamscited by 1
  8. 2026Layout-Aware Representation Learning for Open-Set ID Fraud Discoverycited by 1
  9. 2023Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classescited by 0
  10. 2024Informed Decision-Making through Advancements in Open Set Recognition and Unknown Sample Detectioncited by 0
  11. 2025Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentationcited by 0
  12. 2026Open-Set Vein Biometric Recognition with Deep Metric Learningcited by 0
  13. 2026UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attackscited by 0