Consensus Clustering With Unsupervised Representation Learning

TL;DR

This paper investigates the clustering capabilities of BYOL, a self-supervised learning method, and introduces a new loss function to enhance its performance in clustering tasks, outperforming existing methods on standard datasets.

Contribution

The paper proposes a novel consensus clustering loss for BYOL, improving its clustering performance in an end-to-end training framework.

Findings

BYOL features are not optimal for clustering

The proposed loss improves clustering performance

Outperforms similar methods on benchmark datasets

Abstract

Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or have a similar cluster assignment. Bootstrap Your Own Latent (BYOL) is one such representation learning algorithm that has achieved state-of-the-art results in self-supervised image classification on ImageNet under the linear evaluation protocol. However, the utility of the learnt features of BYOL to perform clustering is not explored. In this work, we study the clustering ability of BYOL and observe that features learnt using BYOL may not be optimal for clustering. We propose a novel consensus clustering based loss function, and train BYOL with the proposed loss in an end-to-end way that improves the clustering ability and outperforms similar clustering based methods on some popular computer vision datasets.