期刊
MULTIMEDIA TOOLS AND APPLICATIONS
卷 81, 期 23, 页码 32723-32738出版社
SPRINGER
DOI: 10.1007/s11042-022-12679-5
关键词
Hyperspectral image classification; Deep learning; Convolutional neural network; Cyclic learning
The classification of remotely sensed hyperspectral images is challenging due to the large number of spectral bands and limited data. This paper proposes a HybridSN model and uses cyclic learning to improve the test performance. The introduction of a new cyclic function further enhances the accuracy of the proposed model.
Classification of remotely sensed hyperspectral images (HSI) is a challenging task due to the presence of a large number of spectral bands and due to the less available data of remotely sensed HSI. The use of 3D-CNN and 2D-CNN layers to extract spectral and spatial features shows good test results. The recently introduced HybridSN model for the classification of remotely sensed hyperspectral images is the best to date compared to the other state-of-the-art models. But the test performance of the HybridSN model decreases significantly with the decrease in training data or number of training epochs. In this paper, we have considered cyclic learning for training of the HybridSN model, which shows a significant increase in the test performance of the HybridSN model with 10%, 20%, and 30% training data and limited number of training epochs. Further, we introduce a new cyclic function (ncf) whose training and test performance is comparable to the existing cyclic learning rate policies. More precisely, the proposed HybridSN(ncf ) model has higher average accuracy compared to HybridSN model by 19.47%, 1.81% and 8.33% for Indian Pines, Salinas Scene and University of Pavia datasets respectively in case of 10% training data and limited number of training epochs.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据