EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MDC-MobileNetV3: A Lightweight Multi-Scale Hierarchical Attention Network for Remote Sensing Scene Classification

Haonan Liu, Xiao Wang iD, Jialong Sun, Xingchi Yang iD, Zhilong Wang

Sensors · 02.07.2026 · 26 (13) · 4174

DOI: 10.3390/s26134174 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.07.2026. Verfasst von Haonan Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, China. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Young Foundation of China, Marine Science and Technology Innovation Project of Jiangsu Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing scene classification remains challenging due to substantial object-scale variations, complex background interference, and high inter-class similarity. To address these issues, a lightweight classification framework, termed MDC-MobileNetV3, is proposed based on the MobileNetV3-Large backbone. The framework integrates a Multi-Scale Feature Extraction (MSFE) module for capturing spatial information at different receptive fields, a Dynamic Feature Weighted Fusion (DFWF) mechanism for adaptive feature recalibration, and the hierarchical CBAM attention strategy to enhance discriminative region representation. The model achieved high classification accuracies of 99.52%, 91.54%, 96.48%, 97.35%, 92.43%, and 99.72% on the UC Merced, WHU-RS19, NWPU-Resisc45, AID, CLRS, and PatternNet benchmark datasets, respectively, validating the effectiveness of the proposed framework, while maintaining a lightweight architecture with approximately 4.35 M parameters. In addition, Grad-CAM visualizations indicate that the model effectively focuses on semantically meaningful regions and suppresses irrelevant background information. The results confirm that the proposed framework provides a favorable trade-off between classification accuracy, model lightweight design, and model interpretability for remote sensing scene understanding.

Schlagwörter

Stichwörter der Autor:innen

DFWFMSFEMobileNetV3remote sensing scene classification

Autor:innen und Institutionen

  • School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, China.

ORCID-Profile: Xiao Wang, Xingchi Yang

Förderung

  • National Natural Science Young Foundation of China
  • Marine Science and Technology Innovation Project of Jiangsu Province
  • National Natural Science Foundation of China
  • 'Qing Lan Project' in Jiangsu Universities
  • Qing Lan Project of Jiangsu Universities

Zitieren

APA

Liu, H., Wang, X., Sun, J., Yang, X., & Wang, Z. (2026). MDC-MobileNetV3: A Lightweight Multi-Scale Hierarchical Attention Network for Remote Sensing Scene Classification. Sensors, 26(13), 4174. https://doi.org/10.3390/s26134174

Vancouver

Liu H, Wang X, Sun J, Yang X, Wang Z. MDC-MobileNetV3: A Lightweight Multi-Scale Hierarchical Attention Network for Remote Sensing Scene Classification. Sensors. 2026;26(13):4174. doi:10.3390/s26134174

BibTeX
@article{Liu2026,
  author = {Liu, Haonan and Wang, Xiao and Sun, Jialong and Yang, Xingchi and Wang, Zhilong},
  title = {MDC-MobileNetV3: A Lightweight Multi-Scale Hierarchical Attention Network for Remote Sensing Scene Classification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4174},
  doi = {10.3390/s26134174}
}
Kostenlos starten →