mlsanityData to 7 Oct 2026

Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment

arXiv 2211.02284 ↗First posted 4 Nov 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper proposes Mutual Information Regularized Assignment (MIRA), a pseudo-labeling algorithm for unsupervised representation learning inspired by information maximization. We formulate online pseudo-labeling as an optimization problem to find pseudo-labels that maximize the mutual information between the label and data while being close to a given model probability. We derive a fixed-point iteration method and prove its convergence to the optimal solution. In contrast to baselines, MIRA combined with pseudo-label prediction enables a simple yet effective clustering-based representation learning without incorporating extra training techniques or artificial constraints such as sampling strategy, equipartition constraints, etc. With relatively small training epochs, representation learned by MIRA achieves state-of-the-art performance on various downstream tasks, including the linear/k-NN evaluation and transfer learning. Especially, with only 400 epochs, our method applied to ImageNet dataset with ResNet-50 architecture achieves 75.6% linear evaluation accuracy.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 40 of its 61 references that are in the map. First posted on arXiv 4 Nov 2022.

Builds on

40 of 61 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  12. 2013Describing Textures in the Wildcited by 2,110
28 more
  1. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  2. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  3. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  6. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  7. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  8. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  9. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  10. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  11. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  12. 2017Large Batch Training of Convolutional Networkscited by 529
  13. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  14. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  15. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 324
  16. 2020Whitening for Self-Supervised Representation Learningcited by 278
  17. 2020How Well Do Self-Supervised Models Transfer?cited by 213
  18. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  19. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  20. 2021Solo-learn: A Library of Self-supervised Methods for Visual Representation Learningcited by 116
  21. 2020Self-training Improves Pre-training for Natural Language Understandingcited by 96
  22. 2021ReSSL: Relational Self-Supervised Learning with Weak Augmentationcited by 83
  23. 2019ClusterFit: Improving Generalization of Visual Representationscited by 82
  24. 2021Mean Shift for Self-Supervised Learningcited by 65
  25. 2016CliqueCNN: Deep Unsupervised Exemplar Learningcited by 41
  26. 2021Self-Supervised Classification Networkcited by 27
  27. 2020Unsupervised Representation Learning by InvariancePropagationcited by 18
  28. 2021The fixed point iteration of positive concave mappings converges geometrically if a fixed point exists: implications to wireless systemscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3; 2025: 1.

7 papers.

  1. 2024HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysiscited by 104
  2. 2023A General-Purpose Self-Supervised Model for Computational Pathologycited by 42
  3. 2023SIESTA: Efficient Online Continual Learning with Sleepcited by 24
  4. 2023Representation Learning via Consistent Assignment of Views over Random Partitionscited by 2
  5. 2024Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancingcited by 1
  6. 2024Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identificationcited by 1
  7. 2025A Tutorial on Discriminative Clustering and Mutual Informationcited by 0