Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation

TL;DR

This paper introduces a novel unsupervised domain adaptation method for person re-identification that uses camera style generation and label propagation to effectively reduce domain gaps and improve re-identification accuracy.

Contribution

The paper proposes a camera style adaptation framework combined with a soft-labeling method to address domain shift and non-overlapping labels in person re-identification.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively narrows domain gaps through style transfer.

Improves re-identification accuracy with label propagation.

Abstract

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping labels challenge that source domain and target domain have entirely different persons further increases the re-identification difficulty. In this paper, we propose a novel algorithm to narrow such domain gaps. We derive a camera style adaptation framework to learn the style-based mappings between different camera views, from the target domain to the source domain, and then we can transfer the identity-based distribution from the source domain to the target domain on the camera level. To overcome the non-overlapping labels challenge and guide the person re-identification model to narrow the gap further, an efficient and effective soft-labeling method is proposed to mine the intrinsic local structure of the target domain through building the connection between GAN-translated source domain and the target domain. Experiment results conducted on real benchmark datasets indicate that our method gets state-of-the-art results.