TY - GEN
T1 - Part-Aware Attention Network for Person Re-identification
AU - Xiang, Wangmeng
AU - Jianqiang Huang
AU - Xiansheng Hua
AU - Zhang, Lei
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2020/12
Y1 - 2020/12
N2 - Multi-level feature aggregation and part feature extraction are widely used to boost the performance of person re-identification (Re-ID). Most multi-level feature aggregation methods treat feature maps on different levels equally and use simple local operations for feature fusion, which neglects the long-distance connection among feature maps. On the other hand, the popular horizon pooling part based feature extraction methods may lead to feature misalignment. In this paper, we propose a novel Part-aware Attention Network (PAN) to connect part feature maps and middle-level features. Given a part feature map and a source feature map, PAN uses part features as queries to perform second-order information propagation from the source feature map. The attention is computed based on the compatibility of the source feature map with the part feature map. Specifically, PAN uses high-level part features of different human body parts to aggregate information from mid-level feature maps. As a part-aware feature aggregation method, PAN operates on all spatial positions of feature maps so that it can discover long-distance relations. Extensive experiments show that PAN achieves leading performance on Re-ID benchmarks Market1501, DukeMTMC, and CUHK03.
AB - Multi-level feature aggregation and part feature extraction are widely used to boost the performance of person re-identification (Re-ID). Most multi-level feature aggregation methods treat feature maps on different levels equally and use simple local operations for feature fusion, which neglects the long-distance connection among feature maps. On the other hand, the popular horizon pooling part based feature extraction methods may lead to feature misalignment. In this paper, we propose a novel Part-aware Attention Network (PAN) to connect part feature maps and middle-level features. Given a part feature map and a source feature map, PAN uses part features as queries to perform second-order information propagation from the source feature map. The attention is computed based on the compatibility of the source feature map with the part feature map. Specifically, PAN uses high-level part features of different human body parts to aggregate information from mid-level feature maps. As a part-aware feature aggregation method, PAN operates on all spatial positions of feature maps so that it can discover long-distance relations. Extensive experiments show that PAN achieves leading performance on Re-ID benchmarks Market1501, DukeMTMC, and CUHK03.
UR - https://www.scopus.com/pages/publications/85103278598
U2 - 10.1007/978-3-030-69538-5_9
DO - 10.1007/978-3-030-69538-5_9
M3 - Conference article published in proceeding or book
AN - SCOPUS:85103278598
SN - 9783030695378
T3 - Lecture Notes in Computer Science
SP - 136
EP - 152
BT - Computer Vision – ACCV 2020 - 15th Asian Conference on Computer Vision, 2020, Revised Selected Papers
A2 - Ishikawa, Hiroshi
A2 - Liu, Cheng-Lin
A2 - Pajdla, Tomas
A2 - Shi, Jianbo
PB - Springer Science and Business Media Deutschland GmbH
T2 - 15th Asian Conference on Computer Vision, ACCV 2020
Y2 - 30 November 2020 through 4 December 2020
ER -