Domain Consistency Representation Learning for Lifelong Person Re-Identification
IEEE Transactions on Circuits and Systems for Video Technology · 2026-01 · 36 (1) · 51-62
DOI: 10.1109/tcsvt.2025.3595620 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-01. Verfasst von Shiben Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Liaoning, Liaoning Revitalization Talents Program.
Abstract (Originalsprache)
Lifelong person re-identification (LReID) exhibits a contradictory relationship between intra-domain discrimination and inter-domain gaps when learning from continuous data. Intra-domain discrimination focuses on individual nuances (i.e., clothing type, accessories, etc.), while inter-domain gaps emphasize domain consistency. Achieving a trade-off between maximizing intra-domain discrimination and minimizing inter-domain gaps is a crucial challenge for improving LReID performance. Most existing methods strive to reduce inter-domain gaps through knowledge distillation to maintain domain consistency. However, they often ignore intra-domain discrimination. To address this challenge, we propose a novel domain consistency representation learning (DCR) model that explores global and attribute-wise representations as a bridge to balance intra-domain discrimination and inter-domain gaps. At the intra-domain level, we explore the complementary relationship between global and attribute-wise representations to improve discrimination among similar identities. Excessive learning intra-domain discrimination can lead to catastrophic forgetting. We further develop an attribute-oriented anti-forgetting (AF) strategy that explores attribute-wise representations to enhance inter-domain consistency, and propose a knowledge consolidation (KC) strategy to facilitate knowledge transfer. Extensive experiments show that our DCR achieves superior performance compared to state-of-the-art LReID methods. Our code is available at https://github.com/LiuShiBen/DCR
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program of Liaoning
- Liaoning Revitalization Talents Program
Zitieren
APA
Liu, S., Fan, H., Wang, Q., Ren, W., Tang, Y., & Cong, Y. (2026). Domain Consistency Representation Learning for Lifelong Person Re-Identification. IEEE Transactions on Circuits and Systems for Video Technology, 36(1), 51-62. https://doi.org/10.1109/tcsvt.2025.3595620
Vancouver
Liu S, Fan H, Wang Q, Ren W, Tang Y, Cong Y. Domain Consistency Representation Learning for Lifelong Person Re-Identification. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(1):51-62. doi:10.1109/tcsvt.2025.3595620
BibTeX
@article{Liu2026,
author = {Liu, Shiben and Fan, Huijie and Wang, Qiang and Ren, Weihong and Tang, Yandong and Cong, Yang},
title = {Domain Consistency Representation Learning for Lifelong Person Re-Identification},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {1},
pages = {51--62},
doi = {10.1109/tcsvt.2025.3595620}
}
EUVIMED