TY - JOUR
T1 - Enhancing Person Re-Identification Performance Through in Vivo Learning
AU - Huang, Yan
AU - Wang, Liang
AU - Zhang, Zhang
AU - Wu, Qiang
AU - Zhong, Yi
N1 - Publisher Copyright:
© 1992-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - This research investigates the potential of in vivo learning to enhance visual representation learning for image-based person re-identification (re-ID). Compared to traditional self-supervised learning (which require external data), the introduced in vivo learning utilizes supervisory labels generated from pedestrian images to improve re-ID accuracy without relying on external data sources. Three carefully designed in vivo learning tasks, leveraging statistical regularities within images, are proposed without the need for laborious manual annotations. These tasks enable feature extractors to learn more comprehensive and discriminative person representations by jointly modeling various aspects of human biological structure information, contributing to enhanced re-ID performance. Notably, the method seamlessly integrates with existing re-ID frameworks, requiring minimal modifications and no additional data beyond the existing training set. Extensive experiments on diverse datasets, including Market1501, CUHK03-NP, Celeb-reID, Celeb-reid-light, PRCC, and LTCC, demonstrate substantial enhancements in rank-1 precision compared to state-of-the-art methods.
AB - This research investigates the potential of in vivo learning to enhance visual representation learning for image-based person re-identification (re-ID). Compared to traditional self-supervised learning (which require external data), the introduced in vivo learning utilizes supervisory labels generated from pedestrian images to improve re-ID accuracy without relying on external data sources. Three carefully designed in vivo learning tasks, leveraging statistical regularities within images, are proposed without the need for laborious manual annotations. These tasks enable feature extractors to learn more comprehensive and discriminative person representations by jointly modeling various aspects of human biological structure information, contributing to enhanced re-ID performance. Notably, the method seamlessly integrates with existing re-ID frameworks, requiring minimal modifications and no additional data beyond the existing training set. Extensive experiments on diverse datasets, including Market1501, CUHK03-NP, Celeb-reID, Celeb-reid-light, PRCC, and LTCC, demonstrate substantial enhancements in rank-1 precision compared to state-of-the-art methods.
KW - Person re-identification
KW - boosting performance
KW - in vivo learning
UR - http://www.scopus.com/inward/record.url?scp=85182091203&partnerID=8YFLogxK
U2 - 10.1109/TIP.2023.3341762
DO - 10.1109/TIP.2023.3341762
M3 - Article
C2 - 38109235
AN - SCOPUS:85182091203
SN - 1057-7149
VL - 33
SP - 639
EP - 654
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
ER -