mlsanityData to 14 Oct 2026

Multi-class Classification without Multi-class Labels

arXiv 1901.00544 ↗First posted 2 Jan 2019cs.LG cs.AI cs.CVcited by 100

Not on the map. Why?

Abstract (arXiv)

This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation. The proposed method, meta classification learning, optimizes a binary classifier for pairwise similarity prediction and through this process learns a multi-class classifier as a submodule. We formulate this approach, present a probabilistic graphical model for it, and derive a surprisingly simple loss function that can be used to learn neural network-based models. We then demonstrate that this same framework generalizes to the supervised, unsupervised cross-task, and semi-supervised settings. Our method is evaluated against state of the art in all three learning paradigms and shows a superior or comparable accuracy, providing evidence that learning multi-class classification without multi-class labels is a viable learning option.

Key facts. Cited by 100 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 21; 2023: 24; 2024: 20; 2025: 15; 2026: 5.

100 papers.

Sort:

By area:

  1. 2022Generalized Category Discoverycited by 211
  2. 2021Open-World Semi-Supervised Learningcited by 165
  3. 2021A Unified Objective for Novel Class Discoverycited by 162
  4. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 121
  5. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  6. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  7. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  8. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  9. 2022XCon: Learning with Experts for Fine-grained Category Discoverycited by 50
  10. 2021Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identificationcited by 45
  11. 2022Class-incremental Novel Class Discoverycited by 42
  12. 2022Novel Class Discovery without Forgettingcited by 39
38 more
  1. 2022Towards Robust Ranker for Text Retrievalcited by 37
  2. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  3. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  4. 2022OpenCon: Open-world Contrastive Learningcited by 33
  5. 2021Meta Discovery: Learning to Discover Novel Classes given Very Limited Datacited by 31
  6. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  7. 2023Federated Generalized Category Discoverycited by 27
  8. 2022Modeling Inter-Class and Intra-Class Constraints in Novel Class Discoverycited by 26
  9. 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
  10. 2023Incremental Generalized Category Discoverycited by 25
  11. 2023CLIP-GCD: Simple Language Guided Generalized Category Discoverycited by 25
  12. 2021TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognitioncited by 24
  13. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  14. 2023Class-relation Knowledge Distillation for Novel Class Discoverycited by 23
  15. 2023A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learningcited by 22
  16. 2021Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptationcited by 21
  17. 2023When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysiscited by 21
  18. 2021Learning from Similarity-Confidence Datacited by 19
  19. 2023Novel Class Discovery for Long-tailed Recognitioncited by 19
  20. 2023MOST: Multiple Object localization with Self-supervised Transformers for object discoverycited by 17
  21. 2023Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discoverycited by 16
  22. 2021The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memorycited by 13
  23. 2022A Closer Look at Novel Class Discovery from the Labeled Setcited by 12
  24. 2024CDAD-Net: Bridging Domain Gaps in Generalized Category Discoverycited by 12
  25. 2023Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discoverycited by 11
  26. 2022Spacing Loss for Discovering Novel Categoriescited by 10
  27. 2023A Clustering Framework for Unsupervised and Semi-supervised New Intent Discoverycited by 9
  28. 2024Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discoverycited by 9
  29. 2024AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarioscited by 9
  30. 2022Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptationcited by 8
  31. 2024IntentGPT: Few-shot Intent Discovery with Large Language Modelscited by 8
  32. 2023Towards Unbiased Training in Federated Open-world Semi-supervised Learningcited by 7
  33. 2024A General Framework for Learning from Weak Supervisioncited by 7
  34. 2022A Method for Discovering Novel Classes in Tabular Datacited by 6
  35. 2024Adaptive Discovering and Merging for Incremental Novel Class Discoverycited by 6
  36. 2024New Intent Discovery with Attracting and Dispersing Prototypecited by 6
  37. 2024A Survey of Ontology Expansion for Conversational Understandingcited by 6
  38. 2022Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learningcited by 5

50 most cited of 100 All 100 (JSON)