Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-Identification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-06 · 47 (6) · 4253-4270
DOI: 10.1109/tpami.2025.3538766 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-06. Verfasst von Weizhen He und 10 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key R&D Project of Zhejiang Province.
Abstract (Originalsprache)
Recently, person re-identification (ReID) has witnessed fast development due to its broad practical applications and proposed various settings, e.g., traditional ReID, clothes-changing ReID, and visible-infrared ReID. However, current studies primarily focus on single specific tasks, which limits model applicability in real-world scenarios. This paper aims to address this issue by introducing a novel instruct-ReID task that unifies 6 existing ReID tasks in one model and retrieves images based on provided visual or textual instructions. Instruct-ReID is the first exploration of a general ReID setting, where 6 existing ReID tasks can be viewed as special cases by assigning different instructions. To facilitate research in this new instruct-ReID task, we propose a large-scale OmniReID++ benchmark equipped with diverse data and comprehensive evaluation methods, e.g., task-specific and task-free evaluation settings. In the task-specific evaluation setting, gallery sets are categorized according to specific ReID tasks. We propose a novel baseline model, IRM, with an adaptive triplet loss to handle various retrieval tasks within a unified framework. For task-free evaluation setting, where target person images are retrieved from task-agnostic gallery sets, we further propose a new method called IRM++ with novel memory bank-assisted learning. Extensive evaluations of IRM and IRM++ on OmniReID++ benchmark demonstrate the superiority of our proposed methods, achieving state-of-the-art performance on 10 test sets.
Förderung
- National Natural Science Foundation of China
- Key R&D Project of Zhejiang Province
Zitieren
APA
He, W., Deng, Y., Yan, Y., Zhu, F., Wang, Y., Bai, L., Xie, Q., Zhao, R., Qi, D., Ouyang, W., & Tang, S. (2025). Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(6), 4253-4270. https://doi.org/10.1109/tpami.2025.3538766
Vancouver
He W, Deng Y, Yan Y, Zhu F, Wang Y, Bai L, et al. Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(6):4253-4270. doi:10.1109/tpami.2025.3538766
BibTeX
@article{He2025,
author = {He, Weizhen and Deng, Yiheng and Yan, Yunfeng and Zhu, Feng and Wang, Yizhou and Bai, Lei and Xie, Qingsong and Zhao, Rui and Qi, Donglian and Ouyang, Wanli and Tang, Shixiang},
title = {Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-Identification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {6},
pages = {4253--4270},
doi = {10.1109/tpami.2025.3538766}
}
EUVIMED