Part‐level attention networks for cross‐domain person re‐identification

Abstract 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 mo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qun Zhao, Nisuo Du, Zhi Ouyang, Ning Kang, Ziyan Liu, Xu Wang, Qing He, Yiling Xu, Shichun Ge, Jingkuan Song
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Photography TR1-1050 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/00aded90e8004048b737670ac3b8d9d6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:00aded90e8004048b737670ac3b8d9d6
record_format	dspace
spelling	oai:doaj.org-article:00aded90e8004048b737670ac3b8d9d62021-11-29T03:38:16ZPart‐level attention networks for cross‐domain person re‐identification1751-96671751-965910.1049/ipr2.12292https://doaj.org/article/00aded90e8004048b737670ac3b8d9d62021-12-01T00:00:00Zhttps://doi.org/10.1049/ipr2.12292https://doaj.org/toc/1751-9659https://doaj.org/toc/1751-9667Abstract 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.Qun ZhaoNisuo DuZhi OuyangNing KangZiyan LiuXu WangQing HeYiling XuShichun GeJingkuan SongWileyarticlePhotographyTR1-1050Computer softwareQA76.75-76.765ENIET Image Processing, Vol 15, Iss 14, Pp 3599-3607 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Photography TR1-1050 Computer software QA76.75-76.765
spellingShingle	Photography TR1-1050 Computer software QA76.75-76.765 Qun Zhao Nisuo Du Zhi Ouyang Ning Kang Ziyan Liu Xu Wang Qing He Yiling Xu Shichun Ge Jingkuan Song Part‐level attention networks for cross‐domain person re‐identification
description	Abstract 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.
format	article
author	Qun Zhao Nisuo Du Zhi Ouyang Ning Kang Ziyan Liu Xu Wang Qing He Yiling Xu Shichun Ge Jingkuan Song
author_facet	Qun Zhao Nisuo Du Zhi Ouyang Ning Kang Ziyan Liu Xu Wang Qing He Yiling Xu Shichun Ge Jingkuan Song
author_sort	Qun Zhao
title	Part‐level attention networks for cross‐domain person re‐identification
title_short	Part‐level attention networks for cross‐domain person re‐identification
title_full	Part‐level attention networks for cross‐domain person re‐identification
title_fullStr	Part‐level attention networks for cross‐domain person re‐identification
title_full_unstemmed	Part‐level attention networks for cross‐domain person re‐identification
title_sort	part‐level attention networks for cross‐domain person re‐identification
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/00aded90e8004048b737670ac3b8d9d6
work_keys_str_mv	AT qunzhao partlevelattentionnetworksforcrossdomainpersonreidentification AT nisuodu partlevelattentionnetworksforcrossdomainpersonreidentification AT zhiouyang partlevelattentionnetworksforcrossdomainpersonreidentification AT ningkang partlevelattentionnetworksforcrossdomainpersonreidentification AT ziyanliu partlevelattentionnetworksforcrossdomainpersonreidentification AT xuwang partlevelattentionnetworksforcrossdomainpersonreidentification AT qinghe partlevelattentionnetworksforcrossdomainpersonreidentification AT yilingxu partlevelattentionnetworksforcrossdomainpersonreidentification AT shichunge partlevelattentionnetworksforcrossdomainpersonreidentification AT jingkuansong partlevelattentionnetworksforcrossdomainpersonreidentification
_version_	1718407626286432256

Part‐level attention networks for cross‐domain person re‐identification

Ejemplares similares