Contrastive Mean-Shift Learning for Generalized Category Discovery

TL;DR

This paper introduces Contrastive Mean-Shift (CMS) learning, a novel approach combining mean-shift clustering with contrastive learning to improve generalized category discovery in partially labeled image collections.

Contribution

It revisits mean-shift clustering within a contrastive learning framework, enabling effective clustering with unknown class counts and achieving state-of-the-art results.

Findings

State-of-the-art performance on six GCD benchmarks

Effective clustering with unknown number of classes

Improved representation quality for generalized category discovery

Abstract

We address the problem of generalized category discovery (GCD) that aims to partition a partially labeled collection of images; only a small part of the collection is labeled and the total number of target classes is unknown. To address this generalized image clustering problem, we revisit the mean-shift algorithm, i.e., a classic, powerful technique for mode seeking, and incorporate it into a contrastive learning framework. The proposed method, dubbed Contrastive Mean-Shift (CMS) learning, trains an image encoder to produce representations with better clustering properties by an iterative process of mean shift and contrastive update. Experiments demonstrate that our method, both in settings with and without the total number of clusters being known, achieves state-of-the-art performance on six public GCD benchmarks without bells and whistles.