EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SEFANet: Spectrum-Enhanced Feature Aggregation Network for Salient Object Detection in Hyperspectral Images

Kaihong Chen, Zhen Wang, Xuqi Wang, Shan-Wen Zhang

IEEE Access · 2026 · 14 · 44872-44885

DOI: 10.1109/access.2026.3672882 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Kaihong Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Program of National Social Science Foundation of China, Neural Science Foundation of Shaanxi Province, Scientific Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Salient object detection in hyperspectral images (HSIs) is critical for applications in remote sensing, national defence, and environmental monitoring. However, the high dimensionality of HSIs, background interference, and scale variations pose significant challenges for traditional methods in effectively extracting spectral features and fusing spatial information. To address these issues, we propose a novel Spectrum-Enhanced Feature Aggregation Network (SEFANet) for hyperspectral salient object detection (HSOD). SEFANet adopts a dual-channel, dual-encoder architecture: the main channel leverages a High-Resolution Attention (HRA) module to model spatial and channel dependencies, while the auxiliary channel integrates a Feature Aggregation and Selection (FAS) module to progressively aggregate spectral features. Additionally, the Spectral Sensing Enhancement (SSE) module deeply fuses spatial and spectral information, enhancing robustness against background interference and scale variations. Extensive experiments on the HSOD-BIT dataset demonstrate that SEFANet achieves state-of-the-art performance, with an accuracy of 96.6%, mean intersection over union (mIoU) of 85.3%, mean Dice coefficient (mDice) of 88.1%, and a mean absolute error (MAE) of just 0.039. Compared to existing methods, SEFANet achieves significant improvements in both detection precision and robustness. The source code and dataset will be available on https://github.com/darkseid-arch/SEFANet

Förderung

  • Key Program of National Social Science Foundation of China
  • Neural Science Foundation of Shaanxi Province
  • Scientific Research
  • Education Department of Shaanxi Provincial Government

Zitieren

APA

Chen, K., Wang, Z., Wang, X., & Zhang, S. (2026). SEFANet: Spectrum-Enhanced Feature Aggregation Network for Salient Object Detection in Hyperspectral Images. IEEE Access, 14, 44872-44885. https://doi.org/10.1109/access.2026.3672882

Vancouver

Chen K, Wang Z, Wang X, Zhang S. SEFANet: Spectrum-Enhanced Feature Aggregation Network for Salient Object Detection in Hyperspectral Images. IEEE Access. 2026;14:44872-44885. doi:10.1109/access.2026.3672882

BibTeX
@article{Chen2026,
  author = {Chen, Kaihong and Wang, Zhen and Wang, Xuqi and Zhang, Shan-Wen},
  title = {SEFANet: Spectrum-Enhanced Feature Aggregation Network for Salient Object Detection in Hyperspectral Images},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {44872--44885},
  doi = {10.1109/access.2026.3672882}
}
Kostenlos starten →