mlsanityData to 7 Oct 2026

SCAN: Learning to Classify Images without Labels

arXiv 2005.12320 ↗First posted 25 May 2020cs.CV cs.LGcited by 351

Not on the map. Why?

Abstract (arXiv)

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fashion. In this paper, we deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task from representation learning is employed to obtain semantically meaningful features. Second, we use the obtained features as a prior in a learnable clustering approach. In doing so, we remove the ability for cluster learning to depend on low-level features, which is present in current end-to-end learning approaches. Experimental evaluation shows that we outperform state-of-the-art methods by large margins, in particular +26.6% on CIFAR10, +25.0% on CIFAR100-20 and +21.3% on STL10 in terms of classification accuracy. Furthermore, our method is the first to perform well on a large-scale dataset for image classification. In particular, we obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime without the use of any ground-truth annotations. The code is made publicly available at https://github.com/wvangansbeke/Unsupervised-Classification.

Key facts. Cited by 351 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 69; 2022: 69; 2023: 81; 2024: 58; 2025: 49; 2026: 25.

351 papers.

Sort:

By area:

  1. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  2. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  3. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  4. 2021Generalized Source-free Domain Adaptationcited by 175
  5. 2021Open-World Semi-Supervised Learningcited by 165
  6. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  7. 2021A Unified Objective for Novel Class Discoverycited by 161
  8. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  9. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  10. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  11. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  12. 2021Efficient Training of Visual Transformers with Small Datasetscited by 107
38 more
  1. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  2. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  3. 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
  4. 2022Adversarial Masking for Self-Supervised Learningcited by 78
  5. 2022Deep Clustering: A Comprehensive Surveycited by 78
  6. 2024Wavelet Convolutions for Large Receptive Fieldscited by 74
  7. 2021Multi-level Feature Learning for Contrastive Multi-view Clusteringcited by 73
  8. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
  9. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  10. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 69
  11. 2021Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learningcited by 68
  12. 2021Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelationcited by 65
  13. 2021Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videoscited by 62
  14. 2022Active Learning Through a Covering Lenscited by 62
  15. 2021Graph Contrastive Clusteringcited by 61
  16. 2022Twin Contrastive Learning for Online Clusteringcited by 60
  17. 2022Visual Recognition with Deep Nearest Centroidscited by 59
  18. 2021Learning Representation for Clustering via Prototype Scattering and Positive Samplingcited by 58
  19. 2022Unified Optimal Transport Framework for Universal Domain Adaptationcited by 57
  20. 2023Diffusion Models Beat GANs on Image Classificationcited by 57
  21. 2022Discovering Object Masks with Transformers for Unsupervised Semantic Segmentationcited by 54
  22. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  23. 2022DeepDPM: Deep Clustering With an Unknown Number of Clusterscited by 52
  24. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  25. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  26. 2021Revisiting Contrastive Methods for Unsupervised Learning of Visual Representationscited by 48
  27. 2022Teaching Matters: Investigating the Role of Supervision in Vision Transformerscited by 45
  28. 2024LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Modelcited by 43
  29. 2021MiCE: Mixture of Contrastive Experts for Unsupervised Image Clusteringcited by 42
  30. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  31. 2021You Never Cluster Alonecited by 38
  32. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  33. 2023Image Clustering with External Guidancecited by 36
  34. 2023Vocabulary-free Image Classificationcited by 35
  35. 2023Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representationscited by 35
  36. 2023Unsupervised Universal Image Segmentationcited by 34
  37. 2022Grow and Merge: A Unified Framework for Continuous Categories Discoverycited by 33
  38. 2023Exploring the Limits of Deep Image Clustering using Pretrained Modelscited by 33

50 most cited of 351 All 351 (JSON)