A hybrid neural architecture search for hyperspectral image classification
Frontiers in Physics · 08.03.2023 · 11
DOI: 10.3389/fphy.2023.1159266 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Physics, online erschienen am 08.03.2023. Verfasst von Aili Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Convolution neural network (CNN)is widely used in hyperspectral image (HSI) classification. However, the network architecture of CNNs is usually designed manually, which requires careful fine-tuning. Recently, many technologies for neural architecture search (NAS) have been proposed to automatically design networks, further improving the accuracy of HSI classification to a new level. This paper proposes a circular kernel convolution- β -decay regulation NAS-confident learning rate (CK- β NAS-CLR) framework to automatically design the neural network structure for HSI classification. First, this paper constructs a hybrid search space with 12 kinds of operation, which considers the difference between enhanced circular kernel convolution and square kernel convolution in feature acquisition, so as to improve the sensitivity of the network to hyperspectral information features. Then, the β -decay regulation scheme is introduced to enhance the robustness of differential architecture search (DARTS) and reduce the discretization differences in architecture search. Finally, we combined the confidence learning rate strategy to alleviate the problem of performance collapse. The experimental results on public HSI datasets (Indian Pines, Pavia University) show that the proposed NAS method achieves impressive classification performance and effectively improves classification accuracy.
Zitieren
APA
Wang, A., Song, Y., Wu, H., Liu, C., & Iwahori, Y. (2023). A hybrid neural architecture search for hyperspectral image classification. Frontiers in Physics, 11. https://doi.org/10.3389/fphy.2023.1159266
Vancouver
Wang A, Song Y, Wu H, Liu C, Iwahori Y. A hybrid neural architecture search for hyperspectral image classification. Frontiers in Physics. 2023;11. doi:10.3389/fphy.2023.1159266
BibTeX
@article{Wang2023,
author = {Wang, Aili and Song, Yingluo and Wu, Haibin and Liu, Chengyang and Iwahori, Yuji},
title = {A hybrid neural architecture search for hyperspectral image classification},
journal = {Frontiers in Physics},
year = {2023},
volume = {11},
doi = {10.3389/fphy.2023.1159266}
}
EUVIMED