EUVIMEDEUVIMED entdecken
Crossref

Diversity Learning Guided Dual Graph Autoencoder for Unsupervised Hyperspectral Band Selection

Wei Feng, Chang Tang, Cheng Zeng, Xinwang Liu, Junjun Jiang, Xianju Li, Xinzhong Zhu

IEEE Transactions on Circuits and Systems for Video Technology · 2025-12 · 35 (12) · 11740-11753

DOI: 10.1109/tcsvt.2025.3547137 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-12. Verfasst von Wei Feng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Natural Science Foundation of Hubei Province, National Natural Science Foundation of China, Fundamental Research Funds for National Universities, China University of Geosciences, Wuhan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral band selection, aimed at identifying key spectral bands from the original image, is crucial for reducing dimensionality and enhancing computational efficiency in hyperspectral image (HSI) analysis. Graph learning-based methods have attracted considerable attention due to their efficiency in representing structural correlations between bands and their powerful capability to extract features. However, existing methods have limitations in utilizing spatial relationships among bands and learning their discriminative characteristics. To address these limitations, we propose a Diversity Learning Guided Dual Graph Autoencoder (DLG-DGAE) for unsupervised hyperspectral band selection. In our framework, we integrate a Dual Graph Autoencoder (DGAE) module designed to extract information from both the spatial and spectral relationships among bands, thus fully capturing the structural similarity of the bands. Additionally, we introduce a Spectral Diversity Learning (SDL) strategy to reduce redundant information in the latent representation and enhance the discriminative properties of each band. In the final step, we proceed to cluster the fused latent embeddings. Within each cluster, we select the band exhibiting the highest information entropy as the representative band. Through extensive experimentation on three publicly available datasets, our results consistently indicate that the proposed method surpasses other state-of-the-art techniques. The code is available at https://github.com/fengwe1/DLG-DGAE.

Förderung

  • Natural Science Foundation of Hubei Province
  • National Natural Science Foundation of China
  • Fundamental Research Funds for National Universities, China University of Geosciences, Wuhan

Zitieren

APA

Feng, W., Tang, C., Zeng, C., Liu, X., Jiang, J., Li, X., & Zhu, X. (2025). Diversity Learning Guided Dual Graph Autoencoder for Unsupervised Hyperspectral Band Selection. IEEE Transactions on Circuits and Systems for Video Technology, 35(12), 11740-11753. https://doi.org/10.1109/tcsvt.2025.3547137

Vancouver

Feng W, Tang C, Zeng C, Liu X, Jiang J, Li X, et al. Diversity Learning Guided Dual Graph Autoencoder for Unsupervised Hyperspectral Band Selection. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(12):11740-11753. doi:10.1109/tcsvt.2025.3547137

BibTeX
@article{Feng2025,
  author = {Feng, Wei and Tang, Chang and Zeng, Cheng and Liu, Xinwang and Jiang, Junjun and Li, Xianju and Zhu, Xinzhong},
  title = {Diversity Learning Guided Dual Graph Autoencoder for Unsupervised Hyperspectral Band Selection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {12},
  pages = {11740--11753},
  doi = {10.1109/tcsvt.2025.3547137}
}
Kostenlos starten →