The Library
On exploring pose estimation as an auxiliary learning task for Visible–Infrared Person Re-identification
Tools
Miao, Yunqi, Huang, Nianchang, Ma, Xiao, Zhang, Qiang and Han, Jungong (2023) On exploring pose estimation as an auxiliary learning task for Visible–Infrared Person Re-identification. Neurocomputing, 556 . 126652. doi:10.1016/j.neucom.2023.126652 ISSN 0925-2312.
PDF
WRAP-On-exploring-pose-estimation-auxiliary-learning-task-Visible–Infrared-Person-Re-identification-23.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only until 4 August 2024. Contact author directly, specifying your specific needs. - Requires a PDF viewer. Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0. Download (1550Kb) |
Official URL: https://doi.org/10.1016/j.neucom.2023.126652
Abstract
Visible–infrared person re-identification (VI-ReID) has been challenging due to the existence of large discrepancies between visible and infrared modalities. Most pioneering approaches reduce intra-modality variations and inter-modality discrepancies by learning modality-shared features. However, an explicit modality-shared cue, i.e., body keypoints, has not been fully exploited in VI-ReID. Additionally, existing feature learning paradigms imposed constraints on either global features or partitioned feature stripes, which neglect the prediction consistency of global and part features. To address the above problems, we exploit Pose Estimation as an auxiliary learning task to assist VI-ReID in an end-to-end framework. By jointly training these two tasks in a mutually beneficial manner, our model learns higher quality ID-related features. On top of it, the learnings of global features and local features are seamlessly synchronized by Hierarchical Feature Constraint (HFC), where the former supervises the latter using the knowledge distillation strategy. Experimental results on two benchmark VI-ReID datasets show that the proposed method consistently improves state-of-the-art methods by significant margins. Specifically, our method achieves nearly 20% mAP improvements against the state-of-the-art method on the RegDB dataset. Our intriguing findings highlight the usage of auxiliary task learning in VI-ReID. Our source code is available at https://github.com/yoqim/Pose_VIReID.
Item Type: | Journal Article | ||||||||
---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > Q Science (General) T Technology > TA Engineering (General). Civil engineering (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||||
SWORD Depositor: | Library Publications Router | ||||||||
Library of Congress Subject Headings (LCSH): | Deep learning (Machine learning), Biometric identification, Human face recognition (Computer science), Computer vision, Image processing, Image analysis, Pattern recognition systems -- Data processing | ||||||||
Journal or Publication Title: | Neurocomputing | ||||||||
Publisher: | Elsevier | ||||||||
ISSN: | 0925-2312 | ||||||||
Official Date: | 1 November 2023 | ||||||||
Dates: |
|
||||||||
Volume: | 556 | ||||||||
Article Number: | 126652 | ||||||||
DOI: | 10.1016/j.neucom.2023.126652 | ||||||||
Status: | Peer Reviewed | ||||||||
Publication Status: | Published | ||||||||
Re-use Statement: | |||||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||||
Date of first compliant deposit: | 23 October 2023 |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |