论文标题
人重新识别的分支合作OSNET
Branch-Cooperative OSNet for Person Re-Identification
论文作者
论文摘要
对多分支进行了广泛的研究，用于学习人重新识别（RE-ID）的丰富功能表示。在本文中，我们建议对人重新进行的OSNET上的分支合作架构，称为BC-OSNET。通过堆叠四个合作分支机构，即全球分支，一个本地分支，一个关系分支和对比分支，我们为人重新ID获得了强大的功能代表。广泛的实验表明，拟议的BC-OSNET在三个受欢迎的数据集上实现了最先进的性能，包括Market-1501，Dukemtmc-Reid和Cuhk03。特别是，它在CUHK03_LAIBELED上获得了84.0％的地图和87.1％的排名1精度。
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.
