Author:
Wang Aili,Song Yingluo,Wu Haibin,Liu Chengyang,Iwahori Yuji
Abstract
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-βNAS-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.
Subject
Physical and Theoretical Chemistry,General Physics and Astronomy,Mathematical Physics,Materials Science (miscellaneous),Biophysics
Reference21 articles.
1. On improving recurrent neural network for image classification;Chandra,2017
2. Simultaneous feature selection and SVM parameter determination in classification of hyperspectral imagery using Ant Colony Optimization;Samadzadegan;Remote Sens,2012
3. Deep convolutional neural networks for hyperspectral image classification;Hu;J Sensors,2015
4. Deep supervised learning for hyperspectral data classification through convolutional neural networks;Makantasis,2015
5. Hyperspectral image classification using deep pixel-pair features;Li;IEEE Trans Geosci Remote Sensing,2017
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献