Cluster Contrast for Unsupervised Person Re-Identification

TL;DR

This paper introduces Cluster Contrast, a novel unsupervised person re-identification method that uses cluster-level contrast loss to improve clustering consistency, scalability, and performance across multiple datasets.

Contribution

The paper proposes a cluster-level contrast framework that enhances unsupervised re-ID by maintaining clustering consistency and reducing memory usage, applicable to various clustering algorithms.

Findings

Achieves up to 12.1% improvement in mAP on benchmark datasets.

Reduces GPU memory consumption significantly.

Demonstrates robustness across different clustering algorithms.

Abstract

State-of-the-art unsupervised re-ID methods train the neural networks using a memory-based non-parametric softmax loss. Instance feature vectors stored in memory are assigned pseudo-labels by clustering and updated at instance level. However, the varying cluster sizes leads to inconsistency in the updating progress of each cluster. To solve this problem, we present Cluster Contrast which stores feature vectors and computes contrast loss at the cluster level. Our approach employs a unique cluster representation to describe each cluster, resulting in a cluster-level memory dictionary. In this way, the consistency of clustering can be effectively maintained throughout the pipline and the GPU memory consumption can be significantly reduced. Thus, our method can solve the problem of cluster inconsistency and be applicable to larger data sets. In addition, we adopt different clustering algorithms to demonstrate the robustness and generalization of our framework. The application of Cluster Contrast to a standard unsupervised re-ID pipeline achieves considerable improvements of 9.9%, 8.3%, 12.1% compared to state-of-the-art purely unsupervised re-ID methods and 5.5%, 4.8%, 4.4% mAP compared to the state-of-the-art unsupervised domain adaptation re-ID methods on the Market, Duke, and MSMT17 datasets. Code is available at https://github.com/alibaba/cluster-contrast.