Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification

doi:10.1109/TNNLS.2021.3128269

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification
	Yang, Yang1 ; Wang, Guan'an1 ; Tiwari, Prayag 2; Pandey, Hari Mohan 3; Lei, Zhen4,5,6
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2021-11-30
页码	13
通讯作者	Pandey, Hari Mohan(pandeyh@edgehill.ac.uk) ; Lei, Zhen(zlei@nlpr.ia.ac.cn)
摘要	Recently, unsupervised cross-dataset person reidentification (Re-ID) has attracted more and more attention, which aims to transfer knowledge of a labeled source domain to an unlabeled target domain. There are two common frameworks: one is pixel-alignment of transferring low-level knowledge, and the other is feature-alignment of transferring high-level knowledge. In this article, we propose a novel recurrent autoencoder (RAE) framework to unify these two kinds of methods and inherit their merits. Specifically, the proposed RAE includes three modules, i.e., a feature-transfer (FT) module, a pixel-transfer (PT) module, and a fusion module. The FT module utilizes an encoder to map source and target images to a shared feature space. In the space, not only features are identity-discriminative but also the gap between source and target features is reduced. The PT module takes a decoder to reconstruct original images with its features. Here, we hope that the images reconstructed from target features are in the source style. Thus, the low-level knowledge can be propagated to the target domain. After transferring both high- and low-level knowledge with the two proposed modules above, we design another bilinear pooling layer to fuse both kinds of knowledge. Extensive experiments on Market-1501, DukeMTMC-ReID, and MSMT17 datasets show that our method significantly outperforms either pixel-alignment or feature-alignment Re-ID methods and achieves new state-of-the-art results.
关键词	Cameras Measurement Image reconstruction Data models Adaptation models Scalability Lighting Feature fusion generate adversarial nets person reidentification (Re-ID) unsupervised learning
DOI	10.1109/TNNLS.2021.3128269
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2020YFC2003901] ; Chinese National Natural Science Foundation[61806203] ; Chinese National Natural Science Foundation[62106264] ; Chinese National Natural Science Foundation[61872367] ; Chinese National Natural Science Foundation[61976229] ; Chinese National Natural Science Foundation[61876178] ; Academy of Finland[336033] ; Academy of Finland[315896] ; Business Finland[884/31/2018] ; EU H2020[101016775]
项目资助者	National Key Research and Development Program ; Chinese National Natural Science Foundation ; Academy of Finland ; Business Finland ; EU H2020
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000733529600001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46927
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
通讯作者	Pandey, Hari Mohan; Lei, Zhen
作者单位	1.Chinese Acad Sci CASIA, Natl Lab Pattern Recognit NLPR, Inst Automat, Beijing 100190, Peoples R China 2.Aalto Univ, Dept Comp Sci, Espoo 02150, Finland 3.Edge Hill Univ, Dept Comp Sci, Ormskirk L39 4QP, England 4.Chinese Acad Sci CASIA, Natl Lab Pattern Recognit NLPR, Inst Automat, Ctr Biometr & Secur Res CBSR, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China 6.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, Hong Kong Inst Sci & Innovat, Hong Kong, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Yang, Yang,Wang, Guan'an,Tiwari, Prayag,et al. Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:13.
APA	Yang, Yang,Wang, Guan'an,Tiwari, Prayag,Pandey, Hari Mohan,&Lei, Zhen.(2021).Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA	Yang, Yang,et al."Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):13.