EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SDS-Former: A Transformer-Based Method for Semantic Segmentation of Arid Land Remote Sensing Imagery

Yujie Du, Junfu Fan, Kuan Li, Yongrui Li

Algorithms · 22.04.2026 · 19 (5) · 325

DOI: 10.3390/a19050325 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 22.04.2026. Verfasst von Yujie Du und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, State Key Laboratory of Resources and Environmental Information Systems.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation of land use and land cover (LULC) in arid regions remains challenging due to severe class imbalance, fragmented spatial distributions, and high spectral similarity among different land cover types. These characteristics often lead to an information bottleneck in deep segmentation networks and hinder the extraction of discriminative semantic representations. To address these issues, we propose SDS-Former, a lightweight semantic segmentation network specifically designed for remote sensing imagery in arid environments. SDS-Former incorporates an SSM-inspired Lightweight Semantic Enhancement (LSE) module to strengthen contextual modeling and alleviate the loss of discriminative information in deep features. To tackle scale variations, a Dynamic Selective Feature Fusion (DSFF) module is employed in the decoder to adaptively weight and fuse high-level semantics with low-level spatial details. Furthermore, a Feature Refinement Head (FRH) is introduced to enhance boundary localization and improve the recognition of small-scale and sparsely distributed land cover objects. Extensive ablation and comparative experiments demonstrate that SDS-Former consistently outperforms representative semantic segmentation methods across multiple evaluation metrics. On the Tarim Basin dataset, the proposed network achieves a mean Intersection over Union (mIoU) of 82.51% and an F1 score of 86.47%, indicating its superior effectiveness and robustness. Qualitative results further verify that SDS-Former exhibits clear advantages in distinguishing spectrally similar land cover types and preserving the spatial continuity of ground objects in complex arid-region scenes.

Förderung

  • National Natural Science Foundation of China
  • State Key Laboratory of Resources and Environmental Information Systems

Zitieren

APA

Du, Y., Fan, J., Li, K., & Li, Y. (2026). SDS-Former: A Transformer-Based Method for Semantic Segmentation of Arid Land Remote Sensing Imagery. Algorithms, 19(5), 325. https://doi.org/10.3390/a19050325

Vancouver

Du Y, Fan J, Li K, Li Y. SDS-Former: A Transformer-Based Method for Semantic Segmentation of Arid Land Remote Sensing Imagery. Algorithms. 2026;19(5):325. doi:10.3390/a19050325

BibTeX
@article{Du2026,
  author = {Du, Yujie and Fan, Junfu and Li, Kuan and Li, Yongrui},
  title = {SDS-Former: A Transformer-Based Method for Semantic Segmentation of Arid Land Remote Sensing Imagery},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {5},
  pages = {325},
  doi = {10.3390/a19050325}
}
Kostenlos starten →