Fuzzy Multilayer Clustering and Fuzzy Label Regularization for Unsupervised Person Reidentification
文献类型:期刊论文
作者 | Zhang, Zhong3; Huang, Meiyan3; Liu, Shuang3; Xiao, Baihua2; Durrani, Tariq S.1 |
刊名 | IEEE TRANSACTIONS ON FUZZY SYSTEMS |
出版日期 | 2020-07-01 |
卷号 | 28期号:7页码:1356-1368 |
ISSN号 | 1063-6706 |
关键词 | Databases Multilayer perceptrons Nonhomogeneous media Training Feature extraction Clustering algorithms Cameras Fuzzy multilayer clustering (FMC) fuzzy label regularization (FLR) unsupervised person reidentification |
DOI | 10.1109/TFUZZ.2019.2914626 |
通讯作者 | Zhang, Zhong(zhong.zhang8848@gmail.com) |
英文摘要 | Unsupervised person reidentification has received more attention due to its wide real-world applications. In this paper, we propose a novel method named fuzzy multilayer clustering (FMC) for unsupervised person reidentification. The proposed FMC learns a new feature space using a multilayer perceptron for clustering in order to overcome the influence of complex pedestrian images. Meanwhile, the proposed FMC generates fuzzy labels for unlabeled pedestrian images, which simultaneously considers the membership degree and the similarity between the sample and each cluster. We further propose the fuzzy label regularization (FLR) to train the convolutional neural network (CNN) using pedestrian images with fuzzy labels in a supervised manner. The proposed FLR could regularize the CNN training process and reduce the risk of overfitting. The effectiveness of our method is validated on three large-scale person reidentification databases, i.e., Market-1501, DukeMTMC-reID, and CUHK03. |
WOS关键词 | RECOGNITION |
资助项目 | National Natural Science Foundation of China[61501327] ; National Natural Science Foundation of China[61711530240] ; Natural Science Foundation of Tianjin[17JCZDJC30600] ; Fund of Tianjin Normal University[135202RC1703] ; Open Projects Program of National Laboratory of Pattern Recognition[201700001] ; Open Projects Program of National Laboratory of Pattern Recognition[201800002] ; China Scholarship Council[201708120039] ; China Scholarship Council[201708120040] ; Tianjin Higher Education Creative Team Funds Program ; NSFC-Royal Society Grant |
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:000545205300015 |
资助机构 | National Natural Science Foundation of China ; Natural Science Foundation of Tianjin ; Fund of Tianjin Normal University ; Open Projects Program of National Laboratory of Pattern Recognition ; China Scholarship Council ; Tianjin Higher Education Creative Team Funds Program ; NSFC-Royal Society Grant |
源URL | [http://ir.ia.ac.cn/handle/173211/40096] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_影像分析与机器视觉团队 |
通讯作者 | Zhang, Zhong |
作者单位 | 1.Univ Strathclyde, Dept Elect & Elect Engn, Glasgow G1 1XQ, Lanark, Scotland 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Tianjin Normal Univ, Tianjin Key Lab Wireless Mobile Commun & Power Tr, Tianjin 300387, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Zhong,Huang, Meiyan,Liu, Shuang,et al. Fuzzy Multilayer Clustering and Fuzzy Label Regularization for Unsupervised Person Reidentification[J]. IEEE TRANSACTIONS ON FUZZY SYSTEMS,2020,28(7):1356-1368. |
APA | Zhang, Zhong,Huang, Meiyan,Liu, Shuang,Xiao, Baihua,&Durrani, Tariq S..(2020).Fuzzy Multilayer Clustering and Fuzzy Label Regularization for Unsupervised Person Reidentification.IEEE TRANSACTIONS ON FUZZY SYSTEMS,28(7),1356-1368. |
MLA | Zhang, Zhong,et al."Fuzzy Multilayer Clustering and Fuzzy Label Regularization for Unsupervised Person Reidentification".IEEE TRANSACTIONS ON FUZZY SYSTEMS 28.7(2020):1356-1368. |
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。