mlsanityData to 7 Oct 2026

Classification-Reconstruction Learning for Open-Set Recognition

arXiv 1812.04246 ↗First posted 11 Dec 2018cs.CVcited by 146

Not on the map. Why?

Abstract (arXiv)

Open-set classification is a problem of handling `unknown' classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes appear in the test environment. Existing open-set classifiers rely on deep networks trained in a supervised manner on known classes in the training set; this causes specialization of learned representations to known classes and makes it hard to distinguish unknowns from knowns. In contrast, we train networks for joint classification and reconstruction of input data. This enhances the learned representation so as to preserve information useful for separating unknowns from knowns, as well as to discriminate classes of knowns. Our novel Classification-Reconstruction learning for Open-Set Recognition (CROSR) utilizes latent representations for reconstruction and enables robust unknown detection without harming the known-class classification accuracy. Extensive experiments reveal that the proposed method outperforms existing deep open-set classifiers in multiple standard datasets and is robust to diverse outliers. The code is available in https://nae-lab.org/~rei/research/crosr/.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 40; 2023: 25; 2024: 23; 2025: 15; 2026: 8.

146 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  3. 2023Class-Incremental Learning: A Surveycited by 209
  4. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  5. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  6. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  7. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  8. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  9. 2021Zero-Shot Instance Segmentationcited by 40
  10. 2022UC-OWOD: Unknown-Classified Open World Object Detectioncited by 40
  11. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  12. 2021Learning to Detect Every Thing in an Open Worldcited by 37
38 more
  1. 2021Open-world Machine Learning: Applications, Challenges, and Opportunitiescited by 34
  2. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  3. 2022OpenAUC: Towards AUC-Oriented Open-Set Recognitioncited by 33
  4. 2023Progressive Open Space Expansion for Open-Set Model Attributioncited by 32
  5. 2022Class-Specific Semantic Reconstruction for Open Set Recognitioncited by 28
  6. 2021Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approachescited by 27
  7. 2021Learning Bounds for Open-Set Learningcited by 27
  8. 2022PMAL: Open Set Recognition via Robust Prototype Miningcited by 27
  9. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  10. 2021A Survey on Open Set Recognitioncited by 25
  11. 2022Difficulty-Aware Simulator for Open Set Recognitioncited by 24
  12. 2022Few-Shot Continual Active Learning by a Robotcited by 24
  13. 2023Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalizationcited by 24
  14. 2022OpenTAL: Towards Open Set Temporal Action Localizationcited by 23
  15. 2023Entropic Open-set Active Learningcited by 22
  16. 2022Open-set Adversarial Defense with Clean-Adversarial Mutual Learningcited by 21
  17. 2021Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approachcited by 20
  18. 2024Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalizationcited by 20
  19. 2021Conditional Variational Capsule Network for Open Set Recognitioncited by 17
  20. 2022Subsidiary Prototype Alignment for Universal Domain Adaptationcited by 17
  21. 2023Navigating Open Set Scenarios for Skeleton-based Action Recognitioncited by 17
  22. 2021Deep Learning and Traffic Classification: Lessons learned from a commercial-grade dataset with hundreds of encrypted and zero-day applicationscited by 14
  23. 2021CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issuecited by 14
  24. 2022RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detectioncited by 13
  25. 2024Open-Set Recognition in the Age of Vision-Language Modelscited by 13
  26. 2024Open World Object Detection: A Surveycited by 13
  27. 2021M2IOSR: Maximal Mutual Information Open Set Recognitioncited by 12
  28. 2022Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometrycited by 12
  29. 2023SOAR: Scene-debiasing Open-set Action Recognitioncited by 12
  30. 2024Open-Set Biometrics: Beyond Good Closed-Set Modelscited by 12
  31. 2024Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Schedulercited by 12
  32. 2022What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputscited by 11
  33. 2021Collective Decision of One-vs-Rest Networks for Open Set Recognitioncited by 10
  34. 2022Out-of-Distribution Detection for Long-tailed and Fine-grained Skin Lesion Imagescited by 10
  35. 2022Towards Accurate Open-Set Recognition via Background-Class Regularizationcited by 10
  36. 2023LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognitioncited by 10
  37. 2023Unified Classification and Rejection: A One-versus-All Frameworkcited by 9
  38. 2022Dual Decision Improves Open-Set Panoptic Segmentationcited by 8

50 most cited of 146 All 146 (JSON)