中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 生物识别与安全技术研究中心
Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification

文献类型：期刊论文

作者Yang, Yang2; Wang, Guan'an2; Tiwari, Prayag1; Pandey, Hari Mohan3; Lei, Zhen4,5,6
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2021-11-30
页码13
ISSN号2162-237X
关键词Cameras Measurement Image reconstruction Data models Adaptation models Scalability Lighting Feature fusion generate adversarial nets person reidentification (Re-ID) unsupervised learning
DOI10.1109/TNNLS.2021.3128269
通讯作者Pandey, Hari Mohan(pandeyh@edgehill.ac.uk) ; Lei, Zhen(zlei@nlpr.ia.ac.cn)
英文摘要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.
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]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000733529600001
资助机构National Key Research and Development Program ; Chinese National Natural Science Foundation ; Academy of Finland ; Business Finland ; EU H2020
源URL[http://ir.ia.ac.cn/handle/173211/46926]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
通讯作者Pandey, Hari Mohan; Lei, Zhen
作者单位1.Aalto Univ, Dept Comp Sci, Espoo 02150, Finland
2.Chinese Acad Sci CASIA, Natl Lab Pattern Recognit NLPR, Inst Automat, Beijing 100190, Peoples R China
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
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。