Dual Heterogeneous Network for Hyperspectral Image Classification
IEEE Transactions on Circuits and Systems for Video Technology · 2025-03 · 35 (3) · 2905-2917
DOI: 10.1109/tcsvt.2024.3486755 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-03. Verfasst von Mingxin Jin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Young Talent Fund of Association for Science and Technology in Shaanxi, China, Basic and Applied Basic Research Foundation of Guangdong Province.
Abstract (Originalsprache)
Modeling discriminative spectral-spatial features is a key to improving hyperspectral image classification performance. However, existing methods cannot fully characterize the spatial specificity of hyperspectral images, thus making them unable to fully explore the useful information within the image and further improve the discriminative power of features. To address this issue, this work proposes a dual heterogeneous network (DHNet) for hyperspectral image classification. Specifically, the network consists of spatial-specific and spectral-specific branches and captures spectral-spatial features with complementarity by combining convolution and spectral-spatial involution. To better characterize spatial specificity, the spectral-spatial involution modifies the weight parameters based on the center spectral information and neighborhood spatial information of various spatial locations. Besides, two feature calibration modules are proposed. Spatial-specific and spectral-specific weights are generated from the respective branches to calibrate the features captured by the other branches to improve the information interaction between the two branches. The center spectral mapping integrates the spectral features of the target pixel into the feature to suppress the influence of the neighboring disturbing pixels. Experimental results on four datasets indicate that DHNet achieves an accuracy improvement of 1.23%, 2.03%, 2.52%, and 1.77% over the state-of-the-art peers, respectively.
Förderung
- National Natural Science Foundation of China
- Young Talent Fund of Association for Science and Technology in Shaanxi, China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Chunhui Program of Ministry of Education of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Jin, M., Wang, C., & Yuan, Y. (2025). Dual Heterogeneous Network for Hyperspectral Image Classification. IEEE Transactions on Circuits and Systems for Video Technology, 35(3), 2905-2917. https://doi.org/10.1109/tcsvt.2024.3486755
Vancouver
Jin M, Wang C, Yuan Y. Dual Heterogeneous Network for Hyperspectral Image Classification. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(3):2905-2917. doi:10.1109/tcsvt.2024.3486755
BibTeX
@article{Jin2025,
author = {Jin, Mingxin and Wang, Cong and Yuan, Yuan},
title = {Dual Heterogeneous Network for Hyperspectral Image Classification},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {3},
pages = {2905--2917},
doi = {10.1109/tcsvt.2024.3486755}
}
EUVIMED