mlsanityData to 7 Oct 2026

Joint Unsupervised Learning of Deep Representations and Image Clusters

arXiv 1604.03628 ↗First posted 13 Apr 2016cs.CV cs.LGcited by 205

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters. In our framework, successive operations in a clustering algorithm are expressed as steps in a recurrent process, stacked on top of representations output by a Convolutional Neural Network (CNN). During training, image clusters and representations are updated jointly: image clustering is conducted in the forward pass, while representation learning in the backward pass. Our key idea behind this framework is that good representations are beneficial to image clustering and clustering results provide supervisory signals to representation learning. By integrating two processes into a single model with a unified weighted triplet loss and optimizing it end-to-end, we can obtain not only more powerful representations, but also more precise image clusters. Extensive experiments show that our method outperforms the state-of-the-art on image clustering across a variety of image datasets. Moreover, the learned representations generalize well when transferred to other tasks.

Key facts. Cited by 205 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 77; 2022: 39; 2023: 35; 2024: 28; 2025: 19; 2026: 6.

205 papers.

Sort:

By area:

  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  2. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  3. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 324
  4. 2022Context Autoencoder for Self-Supervised Representation Learningcited by 297
  5. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  6. 2021Open-World Semi-Supervised Learningcited by 165
  7. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  8. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
  9. 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
  10. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  11. 2021SEED: Self-supervised Distillation For Visual Representationcited by 132
  12. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
38 more
  1. 2021Are Large-scale Datasets Necessary for Self-Supervised Pre-training?cited by 117
  2. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  3. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  4. 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
  5. 2022Deep Clustering: A Comprehensive Surveycited by 78
  6. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
  7. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 69
  8. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
  9. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  10. 2021Mean Shift for Self-Supervised Learningcited by 65
  11. 2021Graph Contrastive Clusteringcited by 61
  12. 2022Bootstrapped Masked Autoencoders for Vision BERT Pretrainingcited by 60
  13. 2022Twin Contrastive Learning for Online Clusteringcited by 60
  14. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  15. 2021Unsupervised Action Segmentation by Joint Representation Learning and Online Clusteringcited by 48
  16. 2021Incremental False Negative Detection for Contrastive Learningcited by 48
  17. 2022Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentationcited by 47
  18. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  19. 2022HCSC: Hierarchical Contrastive Selective Codingcited by 43
  20. 2021MiCE: Mixture of Contrastive Experts for Unsupervised Image Clusteringcited by 42
  21. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  22. 2021You Never Cluster Alonecited by 38
  23. 2021Geographical Knowledge-driven Representation Learning for Remote Sensing Imagescited by 37
  24. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  25. 2023Image Clustering with External Guidancecited by 36
  26. 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
  27. 2022Improving Self-Supervised Learning by Characterizing Idealized Representationscited by 33
  28. 2021Pseudo-supervised Deep Subspace Clusteringcited by 29
  29. 2021Self-supervised object detection from audio-visual correspondencecited by 29
  30. 2022Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategycited by 29
  31. 2021Self-Supervised Classification Networkcited by 27
  32. 2023Subclass-balancing Contrastive Learning for Long-tailed Recognitioncited by 26
  33. 2022Semantic-Enhanced Image Clusteringcited by 25
  34. 2021Learning a Self-Expressive Network for Subspace Clusteringcited by 24
  35. 2021TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognitioncited by 24
  36. 2022Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Workscited by 24
  37. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  38. 2021Clustering by Maximizing Mutual Information Across Viewscited by 23

50 most cited of 205 All 205 (JSON)