MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering

• Published in: arXiv.org
• Main Authors: Tsung Wei Tsai, Li, Chongxuan, Zhu, Jun
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 05.05.2021
• Subjects: Algorithms; Clustering; Datasets; Learning; Probabilistic models; Semantics

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...