mlsanityData to 14 Oct 2026

ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detection

arXiv 2407.11735 ↗First posted 16 Jul 2024cs.LG cs.CV stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

In open-set semi-supervised learning (OSSL), we consider unlabeled datasets that may contain unknown classes. Existing OSSL methods often use the softmax confidence for classifying data as in-distribution (ID) or out-of-distribution (OOD). Additionally, many works for OSSL rely on ad-hoc thresholds for ID/OOD classification, without considering the statistics of the problem. We propose a new score for ID/OOD classification based on angles in feature space between data and an ID subspace. Moreover, we propose an approach to estimate the conditional distributions of scores given ID or OOD data, enabling probabilistic predictions of data being ID or OOD. These components are put together in a framework for OSSL, termed ProSub, that is experimentally shown to reach SOTA performance on several benchmark problems. Our code is available at https://github.com/walline/prosub.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 48 of its 68 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

48 of 68 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2016Wide Residual Networkscited by 3,070
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  7. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  11. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  12. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
36 more
  1. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  2. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  3. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  4. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  5. 2015Towards Open Set Deep Networkscited by 538
  6. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  7. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  8. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  9. 2015Semi-Supervised Learning with Ladder Networkscited by 247
  10. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  11. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  12. 2021Open-World Semi-Supervised Learningcited by 165
  13. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 148
  14. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  15. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  16. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  17. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  18. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  19. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  20. 2021Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learningcited by 40
  21. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  22. 2022Towards Realistic Semi-Supervised Learningcited by 27
  23. 2022NP-Match: When Neural Processes meet Semi-Supervised Learningcited by 25
  24. 2023IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilizationcited by 23
  25. 2021OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Datacited by 22
  26. 2020They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learningcited by 18
  27. 2023Open-world Semi-supervised Novel Class Discoverycited by 15
  28. 2023ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learningcited by 13
  29. 2022Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Datacited by 11
  30. 2023RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Datacited by 10
  31. 2023SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learningcited by 9
  32. 2022DoubleMatch: Improving Semi-Supervised Learning with Self-Supervisioncited by 8
  33. 2023Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learningcited by 7
  34. 2020How Out-of-Distribution Data Hurts Semi-Supervised Learningcited by 6
  35. 2023Improving Open-Set Semi-Supervised Learning with Self-Supervisioncited by 6
  36. 2023On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 2.

3 papers.

  1. 2024A Review of Pseudo-Labeling for Computer Visioncited by 16
  2. 2026Semi-Supervised Hierarchical Open-Set Classificationcited by 1
  3. 2026Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learningcited by 0