Multi-branch is extensively studied for learning rich feature representation for person re-identification (Re-ID). In this paper, we propose a branch-cooperative architecture over OSNet, termed BC-OSNet, for person Re-ID. By stacking four cooperative branches, namely, a global branch, a local branch, a relational branch and a contrastive branch, we obtain powerful feature representation for person Re-ID. Extensive experiments show that the proposed BC-OSNet achieves state-of-art performance on the three popular datasets, including Market-1501, DukeMTMC-reID and CUHK03. In particular, it achieves mAP of 84.0% and rank-1 accuracy of 87.1% on the CUHK03_labeled.
@article{arxiv.2006.07206,
title = {Branch-Cooperative OSNet for Person Re-Identification},
author = {Lei Zhang and Xiaofu Wu and Suofei Zhang and Zirui Yin},
journal= {arXiv preprint arXiv:2006.07206},
year = {2020}
}