EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TGDHTL: Hyperspectral Image Classification via Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation

Zarrin Mahdavipour, Nashwan Alromema, Abdolraheem Khader, Ghulam Farooque, Ali Ahmed, Mohamed A. Damos

Remote Sensing · 06.01.2026 · 18 (2) · 189

DOI: 10.3390/rs18020189 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 06.01.2026. Verfasst von Zarrin Mahdavipour und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral image (HSI) classification is pivotal for remote sensing applications, including environmental monitoring, precision agriculture, and urban land-use analysis. However, its accuracy is often limited by scarce labeled data, class imbalance, and domain discrepancies between standard RGB and HSI imagery. Although recent deep learning approaches, such as 3D convolutional neural networks (3D-CNNs), transformers, and generative adversarial networks (GANs), show promise, they struggle with spectral fidelity, computational efficiency, and cross-domain adaptation in label-scarce scenarios. To address these challenges, we propose the Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation (TGDHTL) framework. This framework integrates domain-adaptive alignment of RGB and HSI data, efficient synthetic data generation, and multi-scale spectral–spatial modeling. Specifically, a lightweight transformer, guided by Maximum Mean Discrepancy (MMD) loss, aligns feature distributions across domains. A class-conditional diffusion model generates high-quality samples for underrepresented classes in only 15 inference steps, reducing labeled data needs by approximately 25% and computational costs by up to 80% compared to traditional 1000-step diffusion models. Additionally, a Multi-Scale Stripe Attention (MSSA) mechanism, combined with a Graph Convolutional Network (GCN), enhances pixel-level spatial coherence. Evaluated on six benchmark datasets including HJ-1A and WHU-OHS, TGDHTL consistently achieves high overall accuracy (e.g., 97.89% on University of Pavia) with just 11.9 GFLOPs, surpassing state-of-the-art methods. This framework provides a scalable, data-efficient solution for HSI classification under domain shifts and resource constraints.

Förderung

  • Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah

Zitieren

APA

Mahdavipour, Z., Alromema, N., Khader, A., Farooque, G., Ahmed, A., & Damos, M. A. (2026). TGDHTL: Hyperspectral Image Classification via Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation. Remote Sensing, 18(2), 189. https://doi.org/10.3390/rs18020189

Vancouver

Mahdavipour Z, Alromema N, Khader A, Farooque G, Ahmed A, Damos MA. TGDHTL: Hyperspectral Image Classification via Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation. Remote Sensing. 2026;18(2):189. doi:10.3390/rs18020189

BibTeX
@article{Mahdavipour2026,
  author = {Mahdavipour, Zarrin and Alromema, Nashwan and Khader, Abdolraheem and Farooque, Ghulam and Ahmed, Ali and Damos, Mohamed A.},
  title = {TGDHTL: Hyperspectral Image Classification via Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {2},
  pages = {189},
  doi = {10.3390/rs18020189}
}
Kostenlos starten →