MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering

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 emp...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Tsung Wei Tsai, Li, Chongxuan, Zhu, Jun
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 05.05.2021
Subjects
Algorithms
Clustering
Datasets
Learning
Probabilistic models
Semantics
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422