Contrastive Clustering

TL;DR

This paper introduces Contrastive Clustering, a one-stage online method that combines instance- and cluster-level contrastive learning to improve clustering performance on image datasets.

Contribution

It presents a novel end-to-end contrastive clustering approach that jointly learns representations and cluster assignments using a unified contrastive loss.

Findings

Outperforms 17 state-of-the-art clustering methods on six image benchmarks.

Achieves up to 19 ext{ and }39 ext{ extbackslash%} improvements in NMI on CIFAR-10 and CIFAR-100.

Demonstrates effective joint learning of representations and cluster assignments.

Abstract

In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative instance pairs are constructed through data augmentations and then projected into a feature space. Therein, the instance- and cluster-level contrastive learning are respectively conducted in the row and column space by maximizing the similarities of positive pairs while minimizing those of negative ones. Our key observation is that the rows of the feature matrix could be regarded as soft labels of instances, and accordingly the columns could be further regarded as cluster representations. By simultaneously optimizing the instance- and cluster-level contrastive loss, the model jointly learns representations and cluster assignments in an end-to-end manner. Extensive experimental results show that CC remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19\% (39\%) performance improvement compared with the best baseline.