RingFormer-Seg: A Scalable and Context-Preserving Vision Transformer Framework for Semantic Segmentation of Ultra-High-Resolution Remote Sensing Imagery
Remote Sensing · 03.09.2025 · 17 (17) · 3064
DOI: 10.3390/rs17173064 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.09.2025. Verfasst von Zhan Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Semantic segmentation of ultra-high-resolution remote sensing (UHR-RS) imagery plays a critical role in land use and land cover analysis, yet it remains computationally intensive due to the enormous input size and high spatial complexity. Existing studies have commonly employed strategies such as patch-wise processing, multi-scale model architectures, lightweight networks, and representation sparsification to reduce resource demands, but they have often struggled to maintain long-range contextual awareness and scalability for inputs of arbitrary size. To address this, we propose RingFormer-Seg, a scalable Vision Transformer framework that enables long-range context learning through multi-device parallelism in UHR-RS image segmentation. RingFormer-Seg decomposes the input into spatial subregions and processes them through a distributed three-stage pipeline. First, the Saliency-Aware Token Filter (STF) selects informative tokens to reduce redundancy. Next, the Efficient Local Context Module (ELCM) enhances intra-region features via memory-efficient attention. Finally, the Cross-Device Context Router (CDCR) exchanges token-level information across devices to capture global dependencies. Fine-grained detail is preserved through the residual integration of unselected tokens, and a hierarchical decoder generates high-resolution segmentation outputs. We conducted extensive experiments on three benchmarks covering UHR-RS images from 2048 × 2048 to 8192 × 8192 pixels. Results show that our framework achieves top segmentation accuracy while significantly improving computational efficiency across the DeepGlobe, Wuhan, and Guangdong datasets. RingFormer-Seg offers a versatile solution for UHR-RS image segmentation and demonstrates potential for practical deployment in nationwide land cover mapping, supporting informed decision-making in land resource management, environmental policy planning, and sustainable development.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, Z., Shu, D., Gu, G., Hu, W., Wang, R., Chen, X., & Yang, B. (2025). RingFormer-Seg: A Scalable and Context-Preserving Vision Transformer Framework for Semantic Segmentation of Ultra-High-Resolution Remote Sensing Imagery. Remote Sensing, 17(17), 3064. https://doi.org/10.3390/rs17173064
Vancouver
Zhang Z, Shu D, Gu G, Hu W, Wang R, Chen X, et al. RingFormer-Seg: A Scalable and Context-Preserving Vision Transformer Framework for Semantic Segmentation of Ultra-High-Resolution Remote Sensing Imagery. Remote Sensing. 2025;17(17):3064. doi:10.3390/rs17173064
BibTeX
@article{Zhang2025,
author = {Zhang, Zhan and Shu, Daoyu and Gu, Guihe and Hu, Wenkai and Wang, Ru and Chen, Xiaoling and Yang, Bingnan},
title = {RingFormer-Seg: A Scalable and Context-Preserving Vision Transformer Framework for Semantic Segmentation of Ultra-High-Resolution Remote Sensing Imagery},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {17},
pages = {3064},
doi = {10.3390/rs17173064}
}
EUVIMED