Category-Aware Global–Local Semantic Alignment for Remote Sensing Image–Text Retrieval
Remote Sensing · 13.07.2026 · 18 (14) · 2335
DOI: 10.3390/rs18142335 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 13.07.2026. Verfasst von Da Ha und 1 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In remote sensing image–text retrieval (RSITR), precise cross-modal retrieval is often hindered by centroid drift and ambiguous decision boundaries caused by high inter-class visual similarity. To address these bottlenecks, this study proposes a Category-aware Global–Local Semantic Alignment (CGLSA) framework fine-tuned on the CLIP (ViT-B/16) backbone. The architecture orchestrates two complementary mechanisms: Global Semantic Collaborative Alignment that regularizes macro-level category centroids using momentum updates and Bayesian prior calibration, and Local Fine-grained Feature Alignment that refines instance-level matching via dynamic scale adjustment and category-aware topological masks. Extensive evaluations on three major benchmark datasets (RSICD, RSITMD, and UCM-Captions) validate the model’s efficacy. Compared to strictly controlled CLIP-family baselines under equivalent supervised conditions, CGLSA achieves new state-of-the-art performance across all R@K metrics and mean recall. Extensions adapting this robust centroid formation to semi-supervised and open-vocabulary scenarios are identified for future work.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Ha, D., & Zhang, H. (2026). Category-Aware Global–Local Semantic Alignment for Remote Sensing Image–Text Retrieval. Remote Sensing, 18(14), 2335. https://doi.org/10.3390/rs18142335
Vancouver
Ha D, Zhang H. Category-Aware Global–Local Semantic Alignment for Remote Sensing Image–Text Retrieval. Remote Sensing. 2026;18(14):2335. doi:10.3390/rs18142335
BibTeX
@article{Ha2026,
author = {Ha, Da and Zhang, Haisu},
title = {Category-Aware Global–Local Semantic Alignment for Remote Sensing Image–Text Retrieval},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {14},
pages = {2335},
doi = {10.3390/rs18142335}
}
EUVIMED