mlsanityData to 14 Oct 2026

MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering

arXiv 2105.01899 ↗First posted 5 May 2021cs.LG cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

We present Mixture of Contrastive Experts (MiCE), a unified probabilistic clustering framework that simultaneously exploits the discriminative representations learned by contrastive learning and the semantic structures captured by a latent mixture model. Motivated by the mixture of experts, MiCE employs a gating function to partition an unlabeled dataset into subsets according to the latent semantics and multiple experts to discriminate distinct subsets of instances assigned to them in a contrastive learning manner. To solve the nontrivial inference and learning problems caused by the latent variables, we further develop a scalable variant of the Expectation-Maximization (EM) algorithm for MiCE and provide proof of the convergence. Empirically, we evaluate the clustering performance of MiCE on four widely adopted natural image datasets. MiCE achieves significantly better results than various previous methods and a strong contrastive learning baseline.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 42 of its 74 references that are in the map. First posted on arXiv 5 May 2021.

Builds on

42 of 74 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2017Mask R-CNNcited by 7,277
  8. 2013Auto-Encoding Variational Bayescited by 4,053
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  10. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  11. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  12. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
30 more
  1. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  2. 2019Contrastive Multiview Codingcited by 1,301
  3. 2016Colorful Image Colorizationcited by 1,114
  4. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  5. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  6. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  7. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  8. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  9. 2020SCAN: Learning to Classify Images without Labelscited by 352
  10. 2019Revisiting Self-Supervised Visual Representation Learningcited by 251
  11. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  12. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 232
  13. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
  14. 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 220
  15. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  16. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  17. 2017Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimizationcited by 113
  18. 2018Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiencycited by 105
  19. 2019Deep Comprehensive Correlation Mining for Image Clusteringcited by 80
  20. 2018ClusterGAN : Latent Space Clustering in Generative Adversarial Networkscited by 75
  21. 2020GATCluster: Self-Supervised Gaussian-Attention Network for Image Clusteringcited by 32
  22. 2015Stacked What-Where Auto-encoderscited by 20
  23. 2018Max-Mahalanobis Linear Discriminant Analysis Networkscited by 18
  24. 2018Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional Clusteringcited by 14
  25. 2017Deep Unsupervised Clustering Using Mixture of Autoencoderscited by 9
  26. 2019Multi-Modal Deep Clustering: Unsupervised Partitioning of Imagescited by 8
  27. 2018Deep Clustering Based on a Mixture of Autoencoderscited by 7
  28. 2018Graphical Generative Adversarial Networkscited by 5
  29. 2019Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Datacited by 3
  30. 2020DHOG: Deep Hierarchical Object Groupingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 7; 2023: 7; 2024: 8; 2025: 8; 2026: 6.

42 papers.

Sort:

By area:

  1. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 313
  2. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 94
  3. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
  4. 2022Visual Recognition with Deep Nearest Centroidscited by 59
  5. 2021Learning Representation for Clustering via Prototype Scattering and Positive Samplingcited by 58
  6. 2022Neural Manifold Clustering and Embeddingcited by 44
  7. 2021Towards Unsupervised Domain Generalizationcited by 40
  8. 2021You Never Cluster Alonecited by 38
  9. 2023Image Clustering with External Guidancecited by 36
  10. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  11. 2023DivClust: Controlling Diversity in Deep Clusteringcited by 18
  12. 2023Contextually Affinitive Neighborhood Refinery for Deep Clusteringcited by 10
30 more
  1. 2025On the Provable Importance of Gradients for Language-Assisted Image Clusteringcited by 8
  2. 2022Federated Momentum Contrastive Clusteringcited by 7
  3. 2022Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learningcited by 5
  4. 2025Hierarchical Semantic Alignment for Image Clusteringcited by 5
  5. 2024Personalized Clustering via Targeted Representation Learningcited by 4
  6. 2024Deep Clustering with Self-Supervision using Pairwise Similaritiescited by 3
  7. 2021Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clusteringcited by 2
  8. 2022On the Robustness of Deep Clustering Models: Adversarial Attacks and Defensescited by 2
  9. 2023ConstraintMatch for Semi-constrained Clusteringcited by 2
  10. 2024Deep Online Probability Aggregation Clusteringcited by 2
  11. 2025INTENT: Trajectory Prediction Framework with Intention-Guided Contrastive Clusteringcited by 2
  12. 2025You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clusteringcited by 2
  13. 2026Delving into Spectral Clustering with Vision-Language Representationscited by 2
  14. 2026Automatic Discovery of Disease Subgroups by Contrasting with Healthy Controlscited by 2
  15. 2023Sanitized Clustering against Confounding Biascited by 1
  16. 2024Open-World Semi-Supervised Learning for Node Classificationcited by 1
  17. 2025Keep It Light! Simplifying Image Clustering Via Text-Free Adapterscited by 1
  18. 2025Unsupervised Urban Land Use Mapping with Street View Contrastive Clustering and a Geographical Priorcited by 1
  19. 2025Self-Enhanced Image Clustering with Cross-Modal Semantic Consistencycited by 1
  20. 2026Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasetscited by 1
  21. 2021Separating Boundary Points via Structural Regularization for Very Compact Clusterscited by 0
  22. 2023Local Boosting for Weakly-Supervised Learningcited by 0
  23. 2023Grid Jigsaw Representation with CLIP: A New Perspective on Image Clusteringcited by 0
  24. 2024Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype Aggregationcited by 0
  25. 2024Clustering-friendly Representation Learning for Enhancing Salient Featurescited by 0
  26. 2024Dual-Level Cross-Modal Contrastive Clusteringcited by 0
  27. 2025Deep Clustering via Gradual Community Detectioncited by 0
  28. 2026Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centerscited by 0
  29. 2026Universal Guideline-Driven Image Clustering via a Hybrid LLM Agentcited by 0
  30. 2026VLM4Cluster: Benchmarking Deep Clustering In the Era of Vision-Language Pre-trainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Hierarchical Textual Knowledge for Enhanced Image Clustering
  2. 2025Rethinking Sparse Mixture of Experts from a Unified Perspective
  3. 2023Contrastive Knowledge Amalgamation for Unsupervised Image Classification
  4. 2023DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets
  5. 2024Multi-label Cluster Discrimination for Visual Representation Learning
  6. 2026Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization
  7. 2026Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling
  8. 2024Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization