Identity-Compensated Style Distillation for Visible–Infrared Person Re-Identification
IEEE Transactions on Image Processing · 2026 · 35 · 2941-2954
DOI: 10.1109/tip.2026.3672369 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Yongguo Ling und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangxi Natural Science Foundation of China.
Abstract (Originalsprache)
Visible-Infrared Person Re-Identification (VI-ReID) that matches pedestrian images across visible and infrared modalities suffers from substantial modality discrepancies and intra-class variations. While existing methods typically address the modality gap via style alignment, they often lose identity-relevant semantics and overlook fine-grained inter-class nuances, such as body part contours and structural cues around the head, shoulders, or feet. To tackle these challenges, we propose an Identity-Compensated Style Distillation (ICSD) network that enforces cross-modality style consistency and enhances the discriminative power of modality-invariant features. Specifically, ICSD comprises two core components: (1) a Style Knowledge Distillation (SKD) module, which integrates Style Discrepancy Reduction (SDR) and Identity Knowledge Compensation (IKC) to align modality styles while preserving identity-relevant semantics; (2) an Identity Discrimination Amplification (IDA) module, which captures and enhances subtle inter-class differences by refining identity-specific cues, thereby facilitating more accurate discrimination between different pedestrians. Extensive experiments on three public benchmarks-SYSU-MM01, RegDB, and LLCM-demonstrate that ICSD consistently outperforms state-of-the-art methods, validating the effectiveness and complementarity of its components.
Förderung
- National Natural Science Foundation of China
- Guangxi Natural Science Foundation of China
Zitieren
APA
Ling, Y., Hu, Z., Pu, N., Zhong, Z., & Jiang, X. (2026). Identity-Compensated Style Distillation for Visible–Infrared Person Re-Identification. IEEE Transactions on Image Processing, 35, 2941-2954. https://doi.org/10.1109/tip.2026.3672369
Vancouver
Ling Y, Hu Z, Pu N, Zhong Z, Jiang X. Identity-Compensated Style Distillation for Visible–Infrared Person Re-Identification. IEEE Transactions on Image Processing. 2026;35:2941-2954. doi:10.1109/tip.2026.3672369
BibTeX
@article{Ling2026,
author = {Ling, Yongguo and Hu, Zihao and Pu, Nan and Zhong, Zhun and Jiang, Xudong},
title = {Identity-Compensated Style Distillation for Visible–Infrared Person Re-Identification},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {2941--2954},
doi = {10.1109/tip.2026.3672369}
}
EUVIMED