Camera-aware Label Refinement for Unsupervised Person Re-identification

TL;DR

This paper introduces CALR, a camera-aware label refinement framework for unsupervised person re-identification that reduces camera-induced feature distribution discrepancies through intra-camera clustering and feature alignment.

Contribution

The paper proposes a novel camera-aware label refinement method that improves unsupervised person re-ID by reducing camera domain gap via intra-camera clustering and feature distribution alignment.

Findings

CALR outperforms state-of-the-art methods on benchmark datasets.

Intra-camera clustering improves pseudo label reliability.

Camera-alignment module enhances feature consistency across cameras.

Abstract

Unsupervised person re-identification aims to retrieve images of a specified person without identity labels. Many recent unsupervised Re-ID approaches adopt clustering-based methods to measure cross-camera feature similarity to roughly divide images into clusters. They ignore the feature distribution discrepancy induced by camera domain gap, resulting in the unavoidable performance degradation. Camera information is usually available, and the feature distribution in the single camera usually focuses more on the appearance of the individual and has less intra-identity variance. Inspired by the observation, we introduce a \textbf{C}amera-\textbf{A}ware \textbf{L}abel \textbf{R}efinement~(CALR) framework that reduces camera discrepancy by clustering intra-camera similarity. Specifically, we employ intra-camera training to obtain reliable local pseudo labels within each camera, and then refine global labels generated by inter-camera clustering and train the discriminative model using more reliable global pseudo labels in a self-paced manner. Meanwhile, we develop a camera-alignment module to align feature distributions under different cameras, which could help deal with the camera variance further. Extensive experiments validate the superiority of our proposed method over state-of-the-art approaches. The code is accessible at https://github.com/leeBooMla/CALR.