Dual-Level Matching With Outlier Filtering for Unsupervised Visible-Infrared Person Re-Identification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-05 · 47 (5) · 3815-3829
DOI: 10.1109/tpami.2025.3541053 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-05. Verfasst von Mang Ye und 2 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 102 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Innovative Research Group of Hubei Province.
Abstract (Originalsprache)
Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality retrieval task due to the large modality gap. While numerous efforts have been devoted to the supervised setting with a large amount of labeled cross-modality correspondences, few studies have tried to mitigate the modality gap by mining cross-modality correspondences in an unsupervised manner. However, existing works failed to capture the intrinsic relations among samples across two modalities, resulting in limited performance outcomes. In this paper, we propose a novel Progressive Graph Matching (PGM) approach to globally model the cross-modality relationships and instance-level affinities. PGM formulates cross-modality correspondence mining as a graph matching procedure, aiming to integrate global information by minimizing global matching costs. Considering that samples in wrong clusters cannot find reliable cross-modality correspondences by PGM, we further introduce a robust Dual-Level Matching (DLM) mechanism, combining the cluster-level PGM and Nearest Instance-Cluster Searching (NICS) with instance-level affinity optimization. Additionally, we design an Outlier Filter Strategy (OFS) to filter out unreliable cross-modality correspondences based on the dual-level relation constraints. To mitigate false accumulation in cross-modal correspondence learning, an Alternate Cross Contrastive Learning (ACCL) module is proposed to alternately adjust the dominated matching, i.e., visible-to-infrared or infrared-to-visible matching. Empirical results demonstrate the superiority of our unsupervised solution, achieving comparable performance with supervised counterparts.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Innovative Research Group of Hubei Province
Zitieren
APA
Ye, M., Wu, Z., & Du, B. (2025). Dual-Level Matching With Outlier Filtering for Unsupervised Visible-Infrared Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5), 3815-3829. https://doi.org/10.1109/tpami.2025.3541053
Vancouver
Ye M, Wu Z, Du B. Dual-Level Matching With Outlier Filtering for Unsupervised Visible-Infrared Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(5):3815-3829. doi:10.1109/tpami.2025.3541053
BibTeX
@article{Ye2025,
author = {Ye, Mang and Wu, Zesen and Du, Bo},
title = {Dual-Level Matching With Outlier Filtering for Unsupervised Visible-Infrared Person Re-Identification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {5},
pages = {3815--3829},
doi = {10.1109/tpami.2025.3541053}
}
EUVIMED