Papers › Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
Nat Dilokthanakul, Pedro A. M. Mediano, Marta Garnelo, Matthew C. H. Lee, Hugh Salimbeni, Kai Arulkumaran, Murray Shanahan
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Human Pose Forecasting | Human3.6M | GMVAE | ADE | 461 | #29 of 33 | Archive leaderboard | report |
| Human Pose Forecasting | Human3.6M | GMVAE | APD | 6769 | #29 of 33 | Archive leaderboard | report |
| Human Pose Forecasting | Human3.6M | GMVAE | FDE | 555 | #29 of 33 | Archive leaderboard | report |
| Human Pose Forecasting | Human3.6M | GMVAE | MMADE | 524 | #29 of 33 | Archive leaderboard | report |
| Human Pose Forecasting | Human3.6M | GMVAE | MMFDE | 566 | #29 of 33 | Archive leaderboard | report |
| Human Pose Forecasting | HumanEva-I | GMVAE | ADE@2000ms | 305 | #7 of 11 | Archive leaderboard | report |
| Human Pose Forecasting | HumanEva-I | GMVAE | APD@2000ms | 2443 | #7 of 11 | Archive leaderboard | report |
| Human Pose Forecasting | HumanEva-I | GMVAE | FDE@2000ms | 345 | #7 of 11 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections