EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MS-DARNet: A Lightweight Multi-Scale Selective Dilated Attention Residual Network for Remote Sensing Scene Classification

Jiawei Huang, Chengjun Xu

Remote Sensing · 19.04.2026 · 18 (8) · 1235

DOI: 10.3390/rs18081235 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.04.2026. Verfasst von Jiawei Huang und 1 weiteren Autor:innen. Die Arbeit nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution remote sensing image (HRRSI) scene classification faces challenges such as significant target scale variations, complex background interference, and the difficult spatial parsing of dense objects (such as tightly packed buildings in dense residential areas or scattered aircraft on aprons), while existing models struggle to balance computational efficiency and classification accuracy. To address these issues, this paper proposes a lightweight Multi-Scale Selective Dilated Attention Residual Network (MS-DARNet). The model utilizes a Multi-branch Dilated Feature Extraction (MDFE) module, employing parallel convolutional branches with varying dilation rates to dynamically expand the receptive field and collaboratively extract multi-scale features without increasing parameter counts. Furthermore, a Context-Position Aware Attention (CPAA) module is introduced, combining a large kernel decomposition strategy to suppress irrelevant background noise with direction-aware feature aggregation to retain precise spatial coordinates for dense objects. Extensive experiments on the AID, NWPU-RESISC45, and RSD-WHU46 datasets show that MS-DARNet achieves superior classification accuracies of 97.78%, 94.53%, and 94.55%, respectively. Concurrently, it maintains a significantly low complexity of just 2.50 M parameters and 0.5940 GMACs. These findings demonstrate that MS-DARNet effectively achieves an optimal balance between lightweight architecture and exceptional classification performance for complex remote sensing scenes.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangxi Province

Zitieren

APA

Huang, J., & Xu, C. (2026). MS-DARNet: A Lightweight Multi-Scale Selective Dilated Attention Residual Network for Remote Sensing Scene Classification. Remote Sensing, 18(8), 1235. https://doi.org/10.3390/rs18081235

Vancouver

Huang J, Xu C. MS-DARNet: A Lightweight Multi-Scale Selective Dilated Attention Residual Network for Remote Sensing Scene Classification. Remote Sensing. 2026;18(8):1235. doi:10.3390/rs18081235

BibTeX
@article{Huang2026,
  author = {Huang, Jiawei and Xu, Chengjun},
  title = {MS-DARNet: A Lightweight Multi-Scale Selective Dilated Attention Residual Network for Remote Sensing Scene Classification},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {1235},
  doi = {10.3390/rs18081235}
}
Kostenlos starten →