TY - JOUR
T1 - A Novel Semi-Supervised Learning Approach to Pedestrian Reidentification
AU - Han, Hua
AU - Ma, Wenjin
AU - Zhou, Meng Chu
AU - Guo, Qiang
AU - Abusorrah, Abdullah
N1 - Funding Information:
Manuscript received May 19, 2020; revised July 30, 2020; accepted September 2, 2020. Date of publication September 15, 2020; date of current version February 4, 2021. This work was supported in part by the National Nature Science Foundation of China under Grant 61305014 and Grant 61701295; in part by the China Scholarship Council under Grant 201508310033; and in part by the “Chen Guang” Project supported by Shanghai Municipal Education Commission and Shanghai Education Development Foundation under Grant 13CG60; and in part by the Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, Saudi Arabia, under Grant FP-55-42. (Corresponding author: MengChu Zhou.) Hua Han, Wenjin Ma, and Qiang Guo are with the School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China (e-mail: 2070967@mail.dhu.edu.cn; wen-jinma@163.com; imguoqiang@126.com).
Publisher Copyright:
© 2014 IEEE.
PY - 2021/2/15
Y1 - 2021/2/15
N2 - One of the important Internet-of-Things applications is to use image and video to realize automatic people monitoring, surveillance, tracking, and reidentification (Re-ID). Despite some recent advances, pedestrian Re-ID remains a challenging task. Existing algorithms based on fully supervised learning for it usually requires numerous labeled image and video data, while often ignoring the problem of data imbalance. This work proposes a method based on unlabeled samples generated by cycle generative adversarial networks. For a newly generated unlabeled sample, it learns its pseudorelationship between unlabeled samples and labeled ones in a low-dimensional space by using a self-paced learning approach. Then, these unlabeled ones having pseudo-relationship with labeled ones are added in a training set to better mine discriminative information between positive and negative samples, which is in turn used to learn a more effective metric. We name this method as a semi-supervised learning approach based on the built pseudopairwise relations between labeled data and unlabeled one. It can greatly enhance the performance of pedestrian Re-ID in case of insufficient labeled images. By using only about 10% labeled images in a given database, the proposed method obtains higher accuracy than state-of-the-art supervised learning methods using all labeled ones, e.g., deep-learning ones, thus greatly advancing the field of pedestrian Re-ID.
AB - One of the important Internet-of-Things applications is to use image and video to realize automatic people monitoring, surveillance, tracking, and reidentification (Re-ID). Despite some recent advances, pedestrian Re-ID remains a challenging task. Existing algorithms based on fully supervised learning for it usually requires numerous labeled image and video data, while often ignoring the problem of data imbalance. This work proposes a method based on unlabeled samples generated by cycle generative adversarial networks. For a newly generated unlabeled sample, it learns its pseudorelationship between unlabeled samples and labeled ones in a low-dimensional space by using a self-paced learning approach. Then, these unlabeled ones having pseudo-relationship with labeled ones are added in a training set to better mine discriminative information between positive and negative samples, which is in turn used to learn a more effective metric. We name this method as a semi-supervised learning approach based on the built pseudopairwise relations between labeled data and unlabeled one. It can greatly enhance the performance of pedestrian Re-ID in case of insufficient labeled images. By using only about 10% labeled images in a given database, the proposed method obtains higher accuracy than state-of-the-art supervised learning methods using all labeled ones, e.g., deep-learning ones, thus greatly advancing the field of pedestrian Re-ID.
KW - Generative adversarial networks (GANs)
KW - machine learning
KW - pedestrian reidentification (Re-ID)
KW - pseudo-pairwise relations
KW - semi-supervised learning (SSL)
UR - http://www.scopus.com/inward/record.url?scp=85100761403&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100761403&partnerID=8YFLogxK
U2 - 10.1109/JIOT.2020.3024287
DO - 10.1109/JIOT.2020.3024287
M3 - Article
AN - SCOPUS:85100761403
SN - 2327-4662
VL - 8
SP - 3042
EP - 3052
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 4
M1 - 9197649
ER -