EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Attention-Embedded Triple-Fusion Branch CNN for Hyperspectral Image Classification

Erlei Zhang, Jiayi Zhang, Jiaxin Bai, Jiarong Bian, Shaoyi Fang, Tao Zhan, Mingchen Feng

Remote Sensing · 19.04.2023 · 15 (8) · 2150

DOI: 10.3390/rs15082150 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.04.2023. Verfasst von Erlei Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Basic Research Program of Shaanxi Province, Qin Chuangyuan high-level innovation and entrepreneurship talent program of Shaanxi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral imaging (HSI) is widely used in various fields owing to its rich spectral information. Nonetheless, the high dimensionality of HSI and the limited number of labeled data remain significant obstacles to HSI classification technology. To alleviate the above problems, we propose an attention-embedded triple-branch fusion convolutional neural network (AETF-Net) for an HSI classification. The network consists of a spectral attention branch, a spatial attention branch, and a multi-attention fusion branch (MAFB). The spectral branch introduces the cross-channel attention to alleviate the band redundancy problem in high dimensions, while the spatial branch preserves the location information of features and eliminates interfering image elements by a bi-directional spatial attention module. These pre-extracted spectral and spatial attention features are then embedded into a novel MAFB with large kernel decomposition technique. The proposed AETF-Net achieves multi-attention features reuse and extracts more representative and discriminative features. Experimental results on three well-known datasets demonstrate the superiority of the method AETF-Net.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Basic Research Program of Shaanxi Province
  • Qin Chuangyuan high-level innovation and entrepreneurship talent program of Shaanxi
  • Chinese Universities Scientific Fund

Zitieren

APA

Zhang, E., Zhang, J., Bai, J., Bian, J., Fang, S., Zhan, T., & Feng, M. (2023). Attention-Embedded Triple-Fusion Branch CNN for Hyperspectral Image Classification. Remote Sensing, 15(8), 2150. https://doi.org/10.3390/rs15082150

Vancouver

Zhang E, Zhang J, Bai J, Bian J, Fang S, Zhan T, et al. Attention-Embedded Triple-Fusion Branch CNN for Hyperspectral Image Classification. Remote Sensing. 2023;15(8):2150. doi:10.3390/rs15082150

BibTeX
@article{Zhang2023,
  author = {Zhang, Erlei and Zhang, Jiayi and Bai, Jiaxin and Bian, Jiarong and Fang, Shaoyi and Zhan, Tao and Feng, Mingchen},
  title = {Attention-Embedded Triple-Fusion Branch CNN for Hyperspectral Image Classification},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {8},
  pages = {2150},
  doi = {10.3390/rs15082150}
}
Kostenlos starten →