Center-Oriented Prototype Contrastive Clustering

TL;DR

This paper introduces a novel center-oriented prototype contrastive clustering framework that effectively reduces class conflicts and prototype drift, improving clustering performance through dual consistency learning and soft prototype contrastive modules.

Contribution

It proposes a new clustering framework combining soft prototype contrastive and dual consistency modules to enhance cluster discrimination and stability.

Findings

Outperforms state-of-the-art methods on five datasets

Reduces prototype deviation and inter-class conflicts

Ensures transformation-invariant and compact cluster features

Abstract

Contrastive learning is widely used in clustering tasks due to its discriminative representation. However, the conflict problem between classes is difficult to solve effectively. Existing methods try to solve this problem through prototype contrast, but there is a deviation between the calculation of hard prototypes and the true cluster center. To address this problem, we propose a center-oriented prototype contrastive clustering framework, which consists of a soft prototype contrastive module and a dual consistency learning module. In short, the soft prototype contrastive module uses the probability that the sample belongs to the cluster center as a weight to calculate the prototype of each category, while avoiding inter-class conflicts and reducing prototype drift. The dual consistency learning module aligns different transformations of the same sample and the neighborhoods of different samples respectively, ensuring that the features have transformation-invariant semantic information and compact intra-cluster distribution, while providing reliable guarantees for the calculation of prototypes. Extensive experiments on five datasets show that the proposed method is effective compared to the SOTA. Our code is published on https://github.com/LouisDong95/CPCC.