EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MDS3-Net: A Multiscale Spectral–Spatial Sequence Hybrid CNN–Transformer Model for Hyperspectral Image Classification

Taonian Bian, Bin Yang, Yuanjiang Chen, Xuan Zhou, Li Yue, Shunshi Hu

Remote Sensing · 25.03.2026 · 18 (7) · 977

DOI: 10.3390/rs18070977 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 25.03.2026. Verfasst von Taonian Bian und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hunan Provincial Department of Education https://ror.org/05ckg3w11.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral image (HSI) classification faces significant challenges due to the spatial–spectral heterogeneity of land covers and the geometric rigidity of standard convolutions. Although Transformers offer powerful global modeling capabilities, their quadratic computational complexity limits practical efficiency. To address these limitations, this paper proposes a novel hierarchical framework named MDS3-Net (Multiscale Deformable Spectral–Spatial Sequence Network). Specifically, we design a Multiscale Spectral-Deformable Convolution (MSDC) module that adopts a cascaded strategy to sequentially extract discriminative spectral features and adaptively align spatial receptive fields with irregular object boundaries. To capture long-range dependencies efficiently, a Spectral–Spatial Sequence (S3) Encoder is introduced based on a gated large-kernel convolution mechanism, achieving global context modeling with linear complexity. Furthermore, a Dual-Path Feature Extraction (DPFE) module is proposed to perform semantics-preserving dimension reduction via spectral reorganization and spatial attention. Experimental results on four public datasets demonstrate that the proposed MDS3-Net achieves state-of-the-art classification performance and exhibits superior robustness under limited training samples compared to existing methods.

Förderung

  • Hunan Provincial Department of Education https://ror.org/05ckg3w11

Zitieren

APA

Bian, T., Yang, B., Chen, Y., Zhou, X., Yue, L., & Hu, S. (2026). MDS3-Net: A Multiscale Spectral–Spatial Sequence Hybrid CNN–Transformer Model for Hyperspectral Image Classification. Remote Sensing, 18(7), 977. https://doi.org/10.3390/rs18070977

Vancouver

Bian T, Yang B, Chen Y, Zhou X, Yue L, Hu S. MDS3-Net: A Multiscale Spectral–Spatial Sequence Hybrid CNN–Transformer Model for Hyperspectral Image Classification. Remote Sensing. 2026;18(7):977. doi:10.3390/rs18070977

BibTeX
@article{Bian2026,
  author = {Bian, Taonian and Yang, Bin and Chen, Yuanjiang and Zhou, Xuan and Yue, Li and Hu, Shunshi},
  title = {MDS3-Net: A Multiscale Spectral–Spatial Sequence Hybrid CNN–Transformer Model for Hyperspectral Image Classification},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {7},
  pages = {977},
  doi = {10.3390/rs18070977}
}
Kostenlos starten →