mlsanityData to 14 Oct 2026

Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive Inference

arXiv 2405.20829 ↗First posted 31 May 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Open-world semi-supervised learning (OWSSL) extends conventional semi-supervised learning to open-world scenarios by taking account of novel categories in unlabeled datasets. Despite the recent advancements in OWSSL, the success often relies on the assumptions that 1) labeled and unlabeled datasets share the same balanced class prior distribution, which does not generally hold in real-world applications, and 2) unlabeled training datasets are utilized for evaluation, where such transductive inference might not adequately address challenges in the wild. In this paper, we aim to generalize OWSSL by addressing them. Our work suggests that practical OWSSL may require different training settings, evaluation methods, and learning strategies compared to those prevalent in the existing literature.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 56 references that are in the map. First posted on arXiv 31 May 2024.

Builds on

41 of 56 references.

References · 41

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2020Supervised Contrastive Learningcited by 2,829
  6. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  7. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  9. 2020Long-tail learning via logit adjustmentcited by 618
  10. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  11. 2020Understanding the Behaviour of Contrastive Losscited by 398
  12. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
29 more
  1. 2022Generalized Category Discoverycited by 211
  2. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  3. 2021Open-World Semi-Supervised Learningcited by 165
  4. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  5. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 123
  6. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  7. 2019Multi-class Classification without Multi-class Labelscited by 100
  8. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 92
  9. 2022PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discoverycited by 87
  10. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  11. 2022The Hidden Uniform Cluster Prior in Self-Supervised Learningcited by 58
  12. 2024SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuningcited by 51
  13. 2022XCon: Learning with Experts for Fine-grained Category Discoverycited by 50
  14. 2021Self-Damaging Contrastive Learningcited by 48
  15. 2022Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognitioncited by 44
  16. 2023Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Datacited by 44
  17. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  18. 2022OpenCon: Open-world Contrastive Learningcited by 33
  19. 2022Towards Realistic Semi-Supervised Learningcited by 27
  20. 2022Contrastive Learning with Boosted Memorizationcited by 26
  21. 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
  22. 2015Neural network-based clustering using pairwise constraintscited by 22
  23. 2023On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learningcited by 20
  24. 2023Semi-supervised learning made simple with self-supervised clusteringcited by 20
  25. 2023Novel Class Discovery for Long-tailed Recognitioncited by 19
  26. 2023Open-world Semi-supervised Novel Class Discoverycited by 15
  27. 2023Towards Semi-supervised Learning with Non-random Missing Labelscited by 12
  28. 2023Towards Distribution-Agnostic Generalized Category Discoverycited by 12
  29. 2022On Non-Random Missing Labels in Semi-Supervised Learningcited by 11

Built on by

Not cited yet.