GRCD-Net: Guided Global–Local Relational Learning for Few-Shot Fine-Grained and Remote Sensing Scene Classification
Remote Sensing · 19.05.2026 · 18 (10) · 1632
DOI: 10.3390/rs18101632 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.05.2026. Verfasst von Jianfeng Liu und 6 weiteren Autor:innen. Die Arbeit nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research Project Plan for Basic Research Special Fund of Higher Education Institutions in Henan Province, Key Program of Natural Science Foundation of Henan Province.
Abstract (Originalsprache)
Remote sensing scene classification (RSSC) faces severe challenges from data scarcity and complex background clutter. To overcome these limitations, this paper draws inspiration from few-shot fine-grained image classification (FSFGIC) to filter noise and capture subtle details. However, existing methods often process global context and local features separately, which limits their ability to suppress background noise in complex scenes. Consequently, the Guided Relational Cross-Attention Dual-branch Network (GRCD-Net) is proposed. Its core Guided Relational Cross-Attention (GRC) block leverages global semantics to filter local background noise prior to bidirectional feature interaction. Additionally, Iterative Global Relation (IGR) and Patch-level Dual-Metric (PDM) modules are integrated to robustly refine global relations and capture local similarities. Extensive experiments demonstrate that GRCD-Net consistently outperforms baselines by 2–4% on standard FSFGIC benchmarks. Notably, on the challenging NWPU-RESISC45 RSSC dataset, it achieves an 81.39% one-shot accuracy and exceeds current state-of-the-art methods by 7.55%, validating its efficacy for complex Earth observation.
Förderung
- National Natural Science Foundation of China
- Key Research Project Plan for Basic Research Special Fund of Higher Education Institutions in Henan Province
- Key Program of Natural Science Foundation of Henan Province
- Key Research and Development and Promotion of Special (Science and Technology) Project of Henan Province
- Key Scientific Research Project of Higher Education Institutions in Henan Province
Zitieren
APA
Liu, J., Du, Y., Sun, L., Li, X., Si, Y., Song, X., & Zheng, R. (2026). GRCD-Net: Guided Global–Local Relational Learning for Few-Shot Fine-Grained and Remote Sensing Scene Classification. Remote Sensing, 18(10), 1632. https://doi.org/10.3390/rs18101632
Vancouver
Liu J, Du Y, Sun L, Li X, Si Y, Song X, et al. GRCD-Net: Guided Global–Local Relational Learning for Few-Shot Fine-Grained and Remote Sensing Scene Classification. Remote Sensing. 2026;18(10):1632. doi:10.3390/rs18101632
BibTeX
@article{Liu2026,
author = {Liu, Jianfeng and Du, Yibo and Sun, Lifan and Li, Xiaozheng and Si, Yanna and Song, Xiaoli and Zheng, Ruijuan},
title = {GRCD-Net: Guided Global–Local Relational Learning for Few-Shot Fine-Grained and Remote Sensing Scene Classification},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {10},
pages = {1632},
doi = {10.3390/rs18101632}
}
EUVIMED