Deep Unsupervised Clustering with Clustered Generator Model
This addresses a fundamental challenge in machine learning for unsupervised clustering, with incremental improvements in model integration and extension to per-pixel clustering.
The paper tackles unsupervised clustering by proposing a clustered generator model with continuous and discrete latent variables, achieving competitive clustering accuracy and learning disentangled representations for realistic sample generation.
This paper addresses the problem of unsupervised clustering which remains one of the most fundamental challenges in machine learning and artificial intelligence. We propose the clustered generator model for clustering which contains both continuous and discrete latent variables. Discrete latent variables model the cluster label while the continuous ones model variations within each cluster. The learning of the model proceeds in a unified probabilistic framework and incorporates the unsupervised clustering as an inner step without the need for an extra inference model as in existing variational-based models. The latent variables learned serve as both observed data embedding or latent representation for data distribution. Our experiments show that the proposed model can achieve competitive unsupervised clustering accuracy and can learn disentangled latent representations to generate realistic samples. In addition, the model can be naturally extended to per-pixel unsupervised clustering which remains largely unexplored.