A Multimodule Collaborative Framework for Unsupervised Visible–Infrared Person Re-Identification with Channel Enhancement Modality
Sensors · 11.03.2026 · 26 (6) · 1770
DOI: 10.3390/s26061770 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 11.03.2026. Verfasst von Baoshan Sun und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Tiangong University, Tianjin 300387, China. Hauptthemen laut MEDLINE: Infrared Rays, Biometric Identification. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Tianjin, National Undergraduate Training Program for Innovation and Entrepreneurship.
Abstract (Originalsprache)
Unsupervised visible–infrared person re-identification (USL-VI-ReID) plays a pivotal role in cross-modal computer vision applications for intelligent surveillance and public safety. However, the task remains hampered by large modality gaps and limited granularity in feature representations. In particular, channel augmentation (CA) is typically used only for data augmentation, and its potential as an independent input modality remains unexplored. To address these shortcomings, we present a multimodule collaborative USL-VI-ReID framework that explicitly treats CA as a separate input modality. The framework combines four complementary modules. The Person-ReID Adaptive Convolutional Block Attention Module (PA-CBAM) module extracts discriminative features using a two-level attention mechanism that refines salient spatial and channel cues. The Varied Regional Alignment (VRA) module performs cross-modal regional alignment and leverages the Multimodal Assisted Adversarial Learning (MAAL) to reinforce region-level correspondence. The Varied Regional Neighbor Learning (VRNL) implements reliable neighborhood learning via multi-region association to stabilize pseudo-labels and capture local structure. Finally, the Uniform Merging (UM) module merges split clusters through alternating contrastive learning to improve cluster consistency. We evaluate the proposed method on SYSU-MM01 and RegDB. On RegDB’s visible-to-infrared setting, the approach achieves Rank-1 = 93.34%, mean Average Precision (mAP) = 87.55%, and mean Inverse Negative Penalty (mINP) = 76.08%. These results indicate that our method effectively reduces modal discrepancies and increases feature discriminability. It outperforms most existing unsupervised baselines and several supervised approaches, thereby advancing the practical applicability of USL-VI-ReID.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, Tiangong University, Tianjin 300387, China.
- Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, Tiangong University, Tianjin 300387, China.
ORCID-Profile: Baoshan Sun, Liqing Gao
Förderung
- Natural Science Foundation of Tianjin
- National Undergraduate Training Program for Innovation and Entrepreneurship
Zitieren
APA
Sun, B., Du, Y., & Gao, L. (2026). A Multimodule Collaborative Framework for Unsupervised Visible–Infrared Person Re-Identification with Channel Enhancement Modality. Sensors, 26(6), 1770. https://doi.org/10.3390/s26061770
Vancouver
Sun B, Du Y, Gao L. A Multimodule Collaborative Framework for Unsupervised Visible–Infrared Person Re-Identification with Channel Enhancement Modality. Sensors. 2026;26(6):1770. doi:10.3390/s26061770
BibTeX
@article{Sun2026,
author = {Sun, Baoshan and Du, Yi and Gao, Liqing},
title = {A Multimodule Collaborative Framework for Unsupervised Visible–Infrared Person Re-Identification with Channel Enhancement Modality},
journal = {Sensors},
year = {2026},
volume = {26},
number = {6},
pages = {1770},
doi = {10.3390/s26061770}
}
EUVIMED