EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SSTNT: A Spatial–Spectral Similarity Guided Transformer-in-Transformer for Hyperspectral Unmixing

Xinyu Cui, Xinyue Zhang, Aoran Dai, Da Sun

Photonics · 13.03.2026 · 13 (3) · 276

DOI: 10.3390/photonics13030276 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Photonics, online erschienen am 13.03.2026. Verfasst von Xinyu Cui und 3 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Education Department of Jilin Province, Changchun University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision Transformers (ViTs), owing to their strong capability in modeling global contextual dependencies, have been widely adopted in hyperspectral image unmixing (HU). However, standard ViTs process images by partitioning them into non-overlapping patches, which disrupts spatial continuity at the pixel level and neglects the fine-grained structural relationships among pixels within local regions. Consequently, effectively capturing the detailed spatial–spectral features required for accurate unmixing remains challenging. Furthermore, the high computational complexity of global self-attention and its sensitivity to noise limit the applicability of conventional Transformers to HU. To address these issues, we propose a spatial–spectral similarity guided Transformer-in-Transformer (SSTNT) framework. The proposed network adopts a modified TNT architecture, in which the inner Transformer employs a linear self-attention (LSA) mechanism to efficiently exploit pixel-level local features within sliding windows, while the outer Transformer preserves global attention to aggregate contextual information, thereby forming a cooperative local–global optimization scheme. Furthermore, a lightweight spatial–spectral similarity module is introduced to enhance the modeling of neighborhood structures. Finally, spectral reconstruction is achieved through a trainable endmember decoder and a normalized abundance estimation module. Extensive experiments conducted on both synthetic and real hyperspectral datasets demonstrate the effectiveness and robustness of the proposed method.

Förderung

  • Education Department of Jilin Province
  • Changchun University

Zitieren

APA

Cui, X., Zhang, X., Dai, A., & Sun, D. (2026). SSTNT: A Spatial–Spectral Similarity Guided Transformer-in-Transformer for Hyperspectral Unmixing. Photonics, 13(3), 276. https://doi.org/10.3390/photonics13030276

Vancouver

Cui X, Zhang X, Dai A, Sun D. SSTNT: A Spatial–Spectral Similarity Guided Transformer-in-Transformer for Hyperspectral Unmixing. Photonics. 2026;13(3):276. doi:10.3390/photonics13030276

BibTeX
@article{Cui2026,
  author = {Cui, Xinyu and Zhang, Xinyue and Dai, Aoran and Sun, Da},
  title = {SSTNT: A Spatial–Spectral Similarity Guided Transformer-in-Transformer for Hyperspectral Unmixing},
  journal = {Photonics},
  year = {2026},
  volume = {13},
  number = {3},
  pages = {276},
  doi = {10.3390/photonics13030276}
}
Kostenlos starten →