Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization

TL;DR

This paper introduces Camera-based Batch Normalization (CBN), a novel method that reduces distribution gaps among cameras in person re-identification, improving generalization and reducing reliance on costly cross-camera annotations.

Contribution

The paper proposes CBN, a new operator that aligns camera data distributions, enhancing ReID performance and enabling effective use of intra-camera annotations.

Findings

CBN effectively shrinks distribution gaps between cameras.

Improves model generalization to unseen cameras.

Achieves competitive ReID performance using intra-camera annotations.

Abstract

The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras. It strongly demands costly inter-camera annotations, yet the trained models are not guaranteed to transfer well to previously unseen cameras. These problems significantly limit the application of ReID. This paper rethinks the working mechanism of conventional ReID approaches and puts forward a new solution. With an effective operator named Camera-based Batch Normalization (CBN), we force the image data of all cameras to fall onto the same subspace, so that the distribution gap between any camera pair is largely shrunk. This alignment brings two benefits. First, the trained model enjoys better abilities to generalize across scenarios with unseen cameras as well as transfer across multiple training sets. Second, we can rely on intra-camera annotations, which have been undervalued before due to the lack of cross-camera information, to achieve competitive ReID performance. Experiments on a wide range of ReID tasks demonstrate the effectiveness of our approach. The code is available at https://github.com/automan000/Camera-based-Person-ReID.