On exploring pose estimation as an auxiliary learning task for visible–infrared person re-identification

Miao, Y, Huang, N, Ma, X ORCID: https://orcid.org/0000-0003-1318-3590, Zhang, Q and Han, J, 2023. On exploring pose estimation as an auxiliary learning task for visible–infrared person re-identification. Neurocomputing, 556: 126652. ISSN 0925-2312

Text 1822926_Ma.pdf - Post-print Full-text access embargoed until 4 August 2025. Download (1MB)

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.

Item Type:	Journal article
Publication Title:	Neurocomputing
Creators:	Miao, Y., Huang, N., Ma, X., Zhang, Q. and Han, J.
Publisher:	Elsevier BV
Date:	November 2023
Volume:	556
ISSN:	0925-2312
Identifiers:	Number Type 10.1016/j.neucom.2023.126652 DOI 1822926 Other
Divisions:	Schools > Nottingham Business School
Record created by:	Jeremy Silvester
Date Added:	09 Nov 2023 11:51
Last Modified:	09 Nov 2023 11:51
URI:	https://irep.ntu.ac.uk/id/eprint/50336

Actions (login required)

Edit View

Statistics

Views

Downloads