Learning Discriminative Features with Multiple Granularities for Person Re-Identification

被引:955
作者
Wang, Guanshuo [1 ]
Yuan, Yufeng [2 ]
Chen, Xiong [2 ]
Li, Jiwei [2 ]
Zhou, Xi [1 ,2 ]
机构
[1] Shanghai Jiao Tong Univ, Cooperat Medianet Innovat Ctr, Shanghai, Peoples R China
[2] CloudWalk Technol, Guangzhou, Peoples R China
来源
PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18) | 2018年
关键词
Person re-identification; Feature learning; Multi-branch deep network; NETWORK;
D O I
10.1145/3240508.3240552
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Previous part-based methods mainly focus on locating regions with specific pre-defined semantics to learn local representations, which increases learning difficulty but not efficient or robust to scenarios with large variances. In this paper, we propose an end-to-end feature learning strategy integrating discriminative information with various granularities. We carefully design the Multiple Granularity Network (MGN), a multi-branch deep network architecture consisting of one branch for global feature representations and two branches for local feature representations. Instead of learning on semantic regions, we uniformly partition the images into several stripes, and vary the number of parts in different local branches to obtain local feature representations with multiple granularities. Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that our method robustly achieves state-of-the-art performances and outperforms any existing approaches by a large margin. For example, on Market-1501 dataset in single query mode, we obtain a top result of Rank-1/mAP=96.6%/94.2% with this method after re-ranking.
引用
收藏
页码:274 / 282
页数:9
相关论文
共 50 条
  • [1] Ahmed E, 2015, PROC CVPR IEEE, P3908, DOI 10.1109/CVPR.2015.7299016
  • [2] [Anonymous], 2018, CVPR, DOI DOI 10.1109/CVPR.2018.00051
  • [3] [Anonymous], 2017, ARXIV170700798
  • [4] [Anonymous], 2017, CVPR
  • [5] [Anonymous], 2018, ARXIV180105339
  • [6] [Anonymous], 2017, P CVPR JUL
  • [7] [Anonymous], 2016, IEEE C COMP VIS PATT
  • [8] [Anonymous], 2006, CVPR
  • [9] [Anonymous], 2017, P IEEE C COMPUTER VI
  • [10] Multi-Level Factorisation Net for Person Re-Identification
    Chang, Xiaobin
    Hospedales, Timothy M.
    Xiang, Tao
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 2109 - 2118