mlsanityData to 7 Oct 2026

Open-Set Recognition: a Good Closed-Set Classifier is All You Need?

arXiv 2110.06207 ↗First posted 12 Oct 2021cs.CV cs.LGcited by 351

Not on the map. Why?

Abstract (arXiv)

The ability to identify whether or not a test sample belongs to one of the semantic classes in a classifier's training set is critical to practical deployment of the model. This task is termed open-set recognition (OSR) and has received significant attention in recent years. In this paper, we first demonstrate that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes. We find that this relationship holds across loss objectives and architectures, and further demonstrate the trend both on the standard OSR benchmarks as well as on a large-scale ImageNet evaluation. Second, we use this correlation to boost the performance of a maximum logit score OSR 'baseline' by improving its closed-set accuracy, and with this strong baseline achieve state-of-the-art on a number of OSR benchmarks. Similarly, we boost the performance of the existing state-of-the-art method by improving its closed-set accuracy, but the resulting discrepancy with the strong baseline is marginal. Our third contribution is to present the 'Semantic Shift Benchmark' (SSB), which better respects the task of detecting semantic novelty, in contrast to other forms of distribution shift also considered in related sub-fields, such as out-of-distribution detection. On this new evaluation, we again demonstrate that there is negligible difference between the strong baseline and the existing state-of-the-art. Project Page: https://www.robots.ox.ac.uk/~vgg/research/osr/

Key facts. Cited by 351 papers in the map (data through 7 Oct 2026). Builds on 54 of its 73 references that are in the map. First posted on arXiv 12 Oct 2021.

Builds on

54 of 73 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  10. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  11. 2013Describing Textures in the Wildcited by 2,110
  12. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
38 more
  1. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  3. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  4. 2019Natural Adversarial Examplescited by 1,401
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  8. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  9. 2021ImageNet-21K Pretraining for the Massescited by 607
  10. 2015Towards Open Set Deep Networkscited by 533
  11. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  12. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  13. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  14. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  15. 2019Fast AutoAugmentcited by 243
  16. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  17. 2020Classification-Based Anomaly Detection for General Datacited by 210
  18. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  19. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  20. 2018Reducing Network Agnostophobiacited by 165
  21. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  22. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  23. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  24. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  25. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  26. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  27. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  28. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  29. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  30. 2020What makes instance discrimination good for transfer learning?cited by 111
  31. 2020Hybrid Models for Open Set Recognitioncited by 109
  32. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  33. 2017L2-constrained Softmax Loss for Discriminative Face Verificationcited by 96
  34. 2021Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNetcited by 61
  35. 2020Backpropagated Gradient Representations for Anomaly Detectioncited by 54
  36. 2020Concept Generalization in Visual Representation Learningcited by 35
  37. 2019Deep Transfer Learning for Multiple Class Novelty Detectioncited by 33
  38. 2019P-ODN: Prototype based Open Deep Network for Open Set Recognitioncited by 28

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 44; 2023: 89; 2024: 88; 2025: 85; 2026: 42.

351 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  3. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  4. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  5. 2022Generalized Category Discoverycited by 209
  6. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  7. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  8. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  9. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  10. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  11. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  12. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
38 more
  1. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  2. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  3. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  4. 2023No Representation Rules Them All in Category Discoverycited by 61
  5. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  6. 2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 51
  7. 2023A Closer Look at Few-shot Classification Againcited by 46
  8. 2023On Advantages of Mask-level Recognition for Outlier-aware Segmentationcited by 42
  9. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 41
  10. 2022Parametric Information Maximization for Generalized Category Discoverycited by 39
  11. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  12. 2024Contrastive Mean-Shift Learning for Generalized Category Discoverycited by 39
  13. 2022Expanding Low-Density Latent Regions for Open-Set Object Detectioncited by 38
  14. 2023Personalized Federated Learning under Mixture of Distributionscited by 37
  15. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  16. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  17. 2023AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challengecited by 35
  18. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  19. 2022OpenCon: Open-world Contrastive Learningcited by 33
  20. 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
  21. 2022OpenAUC: Towards AUC-Oriented Open-Set Recognitioncited by 33
  22. 2023Detecting Out-of-Distribution Through the Lens of Neural Collapsecited by 33
  23. 2023Progressive Open Space Expansion for Open-Set Model Attributioncited by 32
  24. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  25. 2024Active Generalized Category Discoverycited by 31
  26. 2024COME: Test-time adaption by Conservatively Minimizing Entropycited by 31
  27. 2022Block Selection Method for Using Feature Norm in Out-of-distribution Detectioncited by 30
  28. 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 30
  29. 2025Mahalanobis++: Improving OOD Detection via Feature Normalizationcited by 30
  30. 2022The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methodscited by 28
  31. 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalitiescited by 28
  32. 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
  33. 2024GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discoverycited by 26
  34. 2025Solving the Catastrophic Forgetting Problem in Generalized Category Discoverycited by 26
  35. 2023Incremental Generalized Category Discoverycited by 25
  36. 2023Understanding the Feature Norm for Out-of-Distribution Detectioncited by 25
  37. 2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 24
  38. 2023ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithmscited by 22

50 most cited of 351 All 351 (JSON)