Modeling Sensor Uncertainty in Cross-Modal Contrastive Learning for Pedestrian Re-Identification
American Journal of Machine Learning · 31.01.2026 · 7 (1) · 69-76
DOI: 10.71465/ajml3574 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Machine Learning, online erschienen am 31.01.2026. Verfasst von Ames R. Walker und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Pedestrian re-identification in autonomous driving is affected by heterogeneous sensor conditions and modality-dependent noise. Building on CLIP-based uncertainty-aware modeling, this paper presents a cross-modal contrastive learning framework that aligns visual and textual pedestrian representations while accounting for sensor uncertainty. Modality-specific confidence weights are introduced to reduce the influence of unreliable features during representation learning. The method is evaluated on three autonomous driving datasets, including nuScenes-ReID and two large-scale urban benchmarks, comprising more than 120,000 pedestrian samples and 45,000 identities. Comparisons are conducted against recent vision-only and vision–language baselines, including PCB, MGN, TransReID, and CLIP-based ReID models. Experimental results show improvements of 3.9%–5.0% in rank-1 accuracy and 4.2%–5.6% in mean average precision under low-visibility and adverse weather conditions.
Zitieren
APA
Walker, A. R., Thompson, E. A., & Hughes, D. K. (2026). Modeling Sensor Uncertainty in Cross-Modal Contrastive Learning for Pedestrian Re-Identification. American Journal of Machine Learning, 7(1), 69-76. https://doi.org/10.71465/ajml3574
Vancouver
Walker AR, Thompson EA, Hughes DK. Modeling Sensor Uncertainty in Cross-Modal Contrastive Learning for Pedestrian Re-Identification. American Journal of Machine Learning. 2026;7(1):69-76. doi:10.71465/ajml3574
BibTeX
@article{Walker2026,
author = {Walker, Ames R. and Thompson, Emily A. and Hughes, Daniel K.},
title = {Modeling Sensor Uncertainty in Cross-Modal Contrastive Learning for Pedestrian Re-Identification},
journal = {American Journal of Machine Learning},
year = {2026},
volume = {7},
number = {1},
pages = {69--76},
doi = {10.71465/ajml3574}
}
EUVIMED