mlsanityData to 7 Oct 2026

Learning Placeholders for Open-Set Recognition

arXiv 2103.15086 ↗First posted 28 Mar 2021cs.CVcited by 121

Not on the map. Why?

Abstract (arXiv)

Traditional classifiers are deployed under closed-set setting, with both training and test classes belong to the same set. However, real-world applications probably face the input of unknown categories, and the model will recognize them as known ones. Under such circumstances, open-set recognition is proposed to maintain classification performance on known classes and reject unknowns. The closed-set models make overconfident predictions over familiar known class instances, so that calibration and thresholding across categories become essential issues when extending to an open-set environment. To this end, we proposed to learn PlaceholdeRs for Open-SEt Recognition (Proser), which prepares for the unknown classes by allocating placeholders for both data and classifier. In detail, learning data placeholders tries to anticipate open-set class data, thus transforms closed-set training into open-set training. Besides, to learn the invariant information between target and non-target classes, we reserve classifier placeholders as the class-specific boundary between known and unknown. The proposed Proser efficiently generates novel class by manifold mixup, and adaptively sets the value of reserved open-set classifier during training. Experiments on various datasets validate the effectiveness of our proposed method.

Key facts. Cited by 121 papers in the map (data through 7 Oct 2026). Builds on 19 of its 42 references that are in the map. First posted on arXiv 28 Mar 2021.

Builds on

19 of 42 references.

References · 19

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  5. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  6. 2015Towards Open Set Deep Networkscited by 533
  7. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  8. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  9. 2014Towards Open World Recognitioncited by 226
  10. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  11. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  12. 2017DOC: Deep Open Classification of Text Documentscited by 109
7 more
  1. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  2. 2017Between-class Learning for Image Classificationcited by 50
  3. 2020DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentationcited by 48
  4. 2017Sparse Representation-based Open Set Recognitioncited by 36
  5. 2019Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learningcited by 29
  6. 2017Open-Category Classification by Adversarial Sample Generationcited by 24
  7. 2016Classification under Streaming Emerging New Classes: A Solution using Completely Random Treescited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 43; 2023: 26; 2024: 24; 2025: 16; 2026: 6.

121 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022Language-driven Semantic Segmentationcited by 711
  3. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  4. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  5. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  6. 2023Class-Incremental Learning: A Surveycited by 209
  7. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  8. 2022A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learningcited by 152
  9. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  10. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  11. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  12. 2021PyCIL: A Python Toolbox for Class-Incremental Learningcited by 83
38 more
  1. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  2. 2022Novel Class Discovery without Forgettingcited by 39
  3. 2021Co-Transport for Class-Incremental Learningcited by 38
  4. 2022Expanding Low-Density Latent Regions for Open-Set Object Detectioncited by 38
  5. 2022OpenAUC: Towards AUC-Oriented Open-Set Recognitioncited by 33
  6. 2023Progressive Open Space Expansion for Open-Set Model Attributioncited by 32
  7. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  8. 2022Open-world Semantic Segmentation for LIDAR Point Cloudscited by 29
  9. 2022Class-Specific Semantic Reconstruction for Open Set Recognitioncited by 28
  10. 2022PMAL: Open Set Recognition via Robust Prototype Miningcited by 27
  11. 2022Towards Open Set Video Anomaly Detectioncited by 26
  12. 2022Difficulty-Aware Simulator for Open Set Recognitioncited by 24
  13. 2022OpenTAL: Towards Open Set Temporal Action Localizationcited by 23
  14. 2024Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalizationcited by 20
  15. 2022Your Out-of-Distribution Detection Method is Not Robust!cited by 16
  16. 2023The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognitioncited by 16
  17. 2024WiOpen: A Robust Wi-Fi-based Open-set Gesture Recognition Frameworkcited by 16
  18. 2022Learning Discriminative Representations and Decision Boundaries for Open Intent Detectioncited by 15
  19. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  20. 2022Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometrycited by 12
  21. 2023SOAR: Scene-debiasing Open-set Action Recognitioncited by 12
  22. 2024Open-Set Biometrics: Beyond Good Closed-Set Modelscited by 12
  23. 2022Estimating Soft Labels for Out-of-Domain Intent Detectioncited by 11
  24. 2023Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worldscited by 11
  25. 2025Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Imagescited by 11
  26. 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
  27. 2023LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognitioncited by 10
  28. 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
  29. 2022Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptationcited by 8
  30. 2024Exploring Diverse Representations for Open Set Recognitioncited by 8
  31. 2022Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spottingcited by 7
  32. 2022Measuring Human Perception to Improve Open Set Recognitioncited by 7
  33. 2022Large-Scale Open-Set Classification Protocols for ImageNetcited by 7
  34. 2022Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learningcited by 7
  35. 2023A Survey on Open-Set Image Recognitioncited by 7
  36. 2024OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learningcited by 7
  37. 2022Few-shot Open-set Recognition Using Background as Unknownscited by 6
  38. 2022Detecting the unknown in Object Detectioncited by 6

50 most cited of 121 All 121 (JSON)