mlsanityData to 7 Oct 2026

Learning to Discover Novel Visual Categories via Deep Transfer Clustering

arXiv 1908.09884 ↗First posted 26 Aug 2019cs.CVcited by 223

Not on the map. Why?

Abstract (arXiv)

We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the ambiguity of clustering, and improve the quality of the newly discovered classes. Our contributions are twofold. The first contribution is to extend Deep Embedded Clustering to a transfer learning setting; we also improve the algorithm by introducing a representation bottleneck, temporal ensembling, and consistency. The second contribution is a method to estimate the number of classes in the unlabelled data. This also transfers knowledge from the known classes, using them as probes to diagnose different choices for the number of classes in the unlabelled subset. We thoroughly evaluate our method, substantially outperforming state-of-the-art techniques in a large number of benchmarks, including ImageNet, OmniGlot, CIFAR-100, CIFAR-10, and SVHN.

Key facts. Cited by 223 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 34; 2023: 49; 2024: 51; 2025: 39; 2026: 21.

223 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  3. 2022Generalized Category Discoverycited by 209
  4. 2021Open-World Semi-Supervised Learningcited by 165
  5. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  6. 2021A Unified Objective for Novel Class Discoverycited by 161
  7. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  8. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  9. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  10. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  11. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 90
  12. 2022PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discoverycited by 85
38 more
  1. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  2. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  3. 2023No Representation Rules Them All in Category Discoverycited by 61
  4. 2022A Review of Deep Transfer Learning and Recent Advancementscited by 56
  5. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  6. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  7. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  8. 2022XCon: Learning with Experts for Fine-grained Category Discoverycited by 50
  9. 2021Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptationcited by 47
  10. 2021Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identificationcited by 45
  11. 2022Towards Open-Set Object Detection and Discoverycited by 44
  12. 2022Class-incremental Novel Class Discoverycited by 42
  13. 2021Attention-driven Graph Clustering Networkcited by 40
  14. 2023MetaGCD: Learning to Continually Learn in Generalized Category Discoverycited by 40
  15. 2022Novel Class Discovery without Forgettingcited by 39
  16. 2022Parametric Information Maximization for Generalized Category Discoverycited by 39
  17. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  18. 2024Contrastive Mean-Shift Learning for Generalized Category Discoverycited by 39
  19. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  20. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  21. 2022Generalized Category Discovery with Decoupled Prototypical Networkcited by 35
  22. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  23. 2022OpenCon: Open-world Contrastive Learningcited by 33
  24. 2022Grow and Merge: A Unified Framework for Continuous Categories Discoverycited by 33
  25. 2021Novel Class Discovery in Semantic Segmentationcited by 31
  26. 2021Data-Free Knowledge Transfer: A Surveycited by 31
  27. 2024Active Generalized Category Discoverycited by 31
  28. 2021Meta Discovery: Learning to Discover Novel Classes given Very Limited Datacited by 30
  29. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  30. 2022Towards Realistic Semi-Supervised Learningcited by 27
  31. 2022Modeling Inter-Class and Intra-Class Constraints in Novel Class Discoverycited by 26
  32. 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
  33. 2023Federated Generalized Category Discoverycited by 26
  34. 2024GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discoverycited by 26
  35. 2025Solving the Catastrophic Forgetting Problem in Generalized Category Discoverycited by 26
  36. 2023Incremental Generalized Category Discoverycited by 25
  37. 2021TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognitioncited by 24
  38. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24

50 most cited of 223 All 223 (JSON)