mlsanityData to 7 Oct 2026

Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

arXiv 1611.02648 ↗First posted 8 Nov 2016cs.LG cs.NE stat.MLcited by 219

Not on the map. Why?

Abstract (arXiv)

We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself in our model and leads to cluster degeneracy. We show that a heuristic called minimum information constraint that has been shown to mitigate this effect in VAEs can also be applied to improve unsupervised clustering performance with our model. Furthermore we analyse the effect of this heuristic and provide an intuition of the various processes with the help of visualizations. Finally, we demonstrate the performance of our model on synthetic data, MNIST and SVHN, showing that the obtained clusters are distinct, interpretable and result in achieving competitive performance on unsupervised clustering to the state-of-the-art results.

Key facts. Cited by 219 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 49; 2022: 47; 2023: 40; 2024: 29; 2025: 29; 2026: 25.

219 papers.

Sort:

By area:

  1. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  2. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  3. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  4. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  5. 2021Deep Generative Models in Engineering Design: A Reviewcited by 103
  6. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  7. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  8. 2025EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modelingcited by 85
  9. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
  10. 2022Deep Clustering: A Comprehensive Surveycited by 78
  11. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
  12. 2022Identifiability of deep generative models without auxiliary informationcited by 70
38 more
  1. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 69
  2. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  3. 2021Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelationcited by 65
  4. 2022Verifying the Union of Manifolds Hypothesis for Image Datacited by 62
  5. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  6. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  7. 2024SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizercited by 55
  8. 2024Learning by Reconstruction Produces Uninformative Features For Perceptioncited by 54
  9. 2021Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clusteringcited by 51
  10. 2023Leveraging Future Relationship Reasoning for Vehicle Trajectory Predictioncited by 47
  11. 2024Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connectionscited by 47
  12. 2021MiCE: Mixture of Contrastive Experts for Unsupervised Image Clusteringcited by 42
  13. 2021You Never Cluster Alonecited by 38
  14. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  15. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
  16. 2022Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Spacecited by 32
  17. 2022Motron: Multimodal Probabilistic Human Motion Forecastingcited by 30
  18. 2024Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Modelscited by 29
  19. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
  20. 2023Stochastic Multi-Person 3D Motion Forecastingcited by 28
  21. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  22. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  23. 2021A Deep Variational Approach to Clustering Survival Datacited by 25
  24. 2025A Survey on Human Interaction Motion Generationcited by 25
  25. 2022A Geometric Perspective on Variational Autoencoderscited by 24
  26. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  27. 2021Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidancecited by 21
  28. 2021Better Latent Spaces for Better Autoencoderscited by 20
  29. 2023t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergencecited by 17
  30. 2022HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAEcited by 16
  31. 2021Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classificationcited by 15
  32. 2021TrajeVAE: Controllable Human Motion Generation from Trajectoriescited by 14
  33. 2021Deep Conditional Gaussian Mixture Model for Constrained Clusteringcited by 14
  34. 2021MUGL: Large Scale Multi Person Conditional Action Generation with Locomotioncited by 14
  35. 2022Strongly Augmented Contrastive Clusteringcited by 14
  36. 2022Deep Clustering with Features from Self-Supervised Pretrainingcited by 14
  37. 2021Cauchy-Schwarz Regularized Autoencodercited by 13
  38. 2022Towards Unsupervised Open World Semantic Segmentationcited by 13

50 most cited of 219 All 219 (JSON)