TY - JOUR
T1 - Fuzzy multilayer clustering and fuzzy label regularization for unsupervised person reidentification
AU - Zhang, Zhong
AU - Huang, Meiyan
AU - Liu, Shuang
AU - Xiao, Baihua
AU - Durrani, Tariq S.
N1 - © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2020/7/31
Y1 - 2020/7/31
N2 - 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.
AB - 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.
KW - fuzzy label regularization (FLR)
KW - fuzzy multilayer clustering (FMC)
KW - unsupervised person reidentification
UR - http://www.scopus.com/inward/record.url?scp=85087795252&partnerID=8YFLogxK
U2 - 10.1109/TFUZZ.2019.2914626
DO - 10.1109/TFUZZ.2019.2914626
M3 - Article
AN - SCOPUS:85087795252
SN - 1063-6706
VL - 28
SP - 1356
EP - 1368
JO - IEEE Transactions on Fuzzy Systems
JF - IEEE Transactions on Fuzzy Systems
IS - 7
ER -