Self-Channel Attention Weighted Part for Person Re-Identification

Lin DU  Chang TIAN  Mingyong ZENG  Jiabao WANG  Shanshan JIAO  Qing SHEN  Wei BAI  Aihong LU  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E104-A    No.3    pp.665-670
Publication Date: 2021/03/01
Publicized: 2020/09/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.2020EAL2059
Type of Manuscript: LETTER
Category: Image
part based models,  1x1 convolution,  attention weight,  

Full Text: PDF(1.2MB)>>
Buy this Article

Part based models have been proved to be beneficial for person re-identification (Re-ID) in recent years. Existing models usually use fixed horizontal stripes or rely on human keypoints to get each part, which is not consistent with the human visual mechanism. In this paper, we propose a Self-Channel Attention Weighted Part model (SCAWP) for Re-ID. In SCAWP, we first learn a feature map from ResNet50 and use 1x1 convolution to reduce the dimension of this feature map, which could aggregate the channel information. Then, we learn the weight map of attention within each channel and multiply it with the feature map to get each part. Finally, each part is used for a special identification task to build the whole model. To verify the performance of SCAWP, we conduct experiment on three benchmark datasets, including CUHK03-NP, Market-1501 and DukeMTMC-ReID. SCAWP achieves rank-1/mAP accuracy of 70.4%/68.3%, 94.6%/86.4% and 87.6%/76.8% on three datasets respectively.