Exploring the Camera Bias of Person Re-identification

TL;DR

This paper investigates camera bias in person re-identification models, especially under domain shifts, and proposes simple normalization and training strategies to reduce bias and improve model performance.

Contribution

It reveals how camera bias worsens under data shifts, analyzes why feature normalization helps, and offers practical strategies to mitigate bias in both supervised and unsupervised ReID models.

Findings

Camera bias increases under data distribution shifts.

Feature normalization effectively reduces bias across various factors.

Simple training strategies improve unsupervised ReID performance.

Abstract

We empirically investigate the camera bias of person re-identification (ReID) models. Previously, camera-aware methods have been proposed to address this issue, but they are largely confined to training domains of the models. We measure the camera bias of ReID models on unseen domains and reveal that camera bias becomes more pronounced under data distribution shifts. As a debiasing method for unseen domain data, we revisit feature normalization on embedding vectors. While the normalization has been used as a straightforward solution, its underlying causes and broader applicability remain unexplored. We analyze why this simple method is effective at reducing bias and show that it can be applied to detailed bias factors such as low-level image properties and body angle. Furthermore, we validate its generalizability across various models and benchmarks, highlighting its potential as a simple yet effective test-time postprocessing method for ReID. In addition, we explore the inherent risk of camera bias in unsupervised learning of ReID models. The unsupervised models remain highly biased towards camera labels even for seen domain data, indicating substantial room for improvement. Based on observations of the negative impact of camera-biased pseudo labels on training, we suggest simple training strategies to mitigate the bias. By applying these strategies to existing unsupervised learning algorithms, we show that significant performance improvements can be achieved with minor modifications.