Open AccessPart‐level attention networks for cross‐domain person re‐identification
Author(s) -
Zhao Qun,
Du Nisuo,
Ouyang Zhi,
Kang Ning,
Liu Ziyan,
Wang Xu,
He Qing,
Xu Yiling,
Ge Shichun,
Song Jingkuan
Publication year - 2021
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/ipr2.12292
Subject(s) - computer science , generality , adaptability , domain (mathematical analysis) , artificial intelligence , baseline (sea) , identification (biology) , generalization , machine learning , domain adaptation , set (abstract data type) , feature (linguistics) , data mining , pattern recognition (psychology) , mathematics , psychology , mathematical analysis , ecology , linguistics , oceanography , botany , philosophy , classifier (uml) , psychotherapist , biology , programming language , geology
Person re‐identification (Re‐ID) is in significant demand for intelligent security and single or multiple‐target tracking. However, there are issues in the person Re‐ID tasks, such as sharp decline in cross‐data sets detection accuracy, poor generalization and cross‐domain ability of the model. This work mainly studies the generalization and adaptation of cross‐domain person Re‐ID models. Different from most existing methods for cross‐domain Re‐ID tasks, the authors use diversified spatial semantic feature in pixel‐level learning in the target domain to improve the generality and adaptability of the model. In the case that no information of the target domain is used during the model training, the trained model is directly tested on the data set of the target domain. It has proven effective to add the attention cascade module into the backbone network combining with the part‐level branch. The authors conducted extensive experiments based on the three data sets of Market‐1501, DukeMTMC‐ReID and MSMT17, resulting in both single‐domain and cross‐domain tests with an average improvement of Rank1 and mAP values of about 10% compared with Baseline through the authors' proposed method named Part‐Level Attention Network.