Dual Network Fusion for Person Re-Identification

Lin DU  Chang TIAN  Mingyong ZENG  Jiabao WANG  Shanshan JIAO  Qing SHEN  Guodong WU  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E103-A    No.3    pp.643-648
Publication Date: 2020/03/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.2019EAL2116
Type of Manuscript: LETTER
Category: Image
attention maps,  dual network,  channel attention,  multi-loss training,  

Full Text: PDF>>
Buy this Article

Feature learning based on deep network has been verified as beneficial for person re-identification (Re-ID) in recent years. However, most researches use a single network as the baseline, without considering the fusion of different deep features. By analyzing the attention maps of different networks, we find that the information learned by different networks can complement each other. Therefore, a novel Dual Network Fusion (DNF) framework is proposed. DNF is designed with a trunk branch and two auxiliary branches. In the trunk branch, deep features are cascaded directly along the channel direction. One of the auxiliary branch is channel attention branch, which is used to allocate weight for different deep features. Another one is multi-loss training branch. To verify the performance of DNF, we test it on three benchmark datasets, including CUHK03NP, Market-1501 and DukeMTMC-reID. The results show that the effect of using DNF is significantly better than a single network and is comparable to most state-of-the-art methods.