3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-Identification

TL;DR

This paper introduces 3C, a confidence-guided clustering and contrastive learning framework that improves unsupervised person re-identification by reducing noise and bias, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes a novel 3C framework with three confidence measures to enhance clustering and contrastive learning in unsupervised person Re-ID, addressing noise and bias issues.

Findings

Achieves state-of-the-art mAP and Rank-1 accuracy on Market-1501, MSMT17, and VeRi-776 datasets.

Effectively reduces feature bias, noise pseudo-labels, and hard sample issues in unsupervised Re-ID.

Demonstrates superior performance over existing methods on three popular benchmarks.

Abstract

Unsupervised person re-identification (Re-ID) aims to learn a feature network with cross-camera retrieval capability in unlabelled datasets. Although the pseudo-label based methods have achieved great progress in Re-ID, their performance in the complex scenario still needs to sharpen up. In order to reduce potential misguidance, including feature bias, noise pseudo-labels and invalid hard samples, accumulated during the learning process, in this pa per, a confidence-guided clustering and contrastive learning (3C) framework is proposed for unsupervised person Re-ID. This 3C framework presents three confidence degrees. i) In the clustering stage, the confidence of the discrepancy between samples and clusters is proposed to implement a harmonic discrepancy clustering algorithm (HDC). ii) In the forward-propagation training stage, the confidence of the camera diversity of a cluster is evaluated via a novel camera information entropy (CIE). Then, the clusters with high CIE values will play leading roles in training the model. iii) In the back-propagation training stage, the confidence of the hard sample in each cluster is designed and further used in a confidence integrated harmonic discrepancy (CHD), to select the informative sample for updating the memory in contrastive learning. Extensive experiments on three popular Re-ID benchmarks demonstrate the superiority of the proposed framework. Particularly, the 3C framework achieves state-of-the-art results: 86.7%/94.7%, 45.3%/73.1% and 47.1%/90.6% in terms of mAP/Rank-1 accuracy on Market-1501, the com plex datasets MSMT17 and VeRi-776, respectively. Code is available at https://github.com/stone5265/3C-reid.