Deep Unsupervised Clustering with Clustered Generator Model

TL;DR

This paper introduces a novel clustered generator model for unsupervised clustering that uses both discrete and continuous latent variables, achieving competitive accuracy and enabling extensions like per-pixel clustering.

Contribution

The proposed model integrates clustering into a unified probabilistic framework without extra inference models, advancing unsupervised clustering and representation learning.

Findings

Achieves competitive clustering accuracy

Learns disentangled latent representations

Enables per-pixel unsupervised clustering

Abstract

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.