期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 56, 期 2, 页码 847-858出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2017.2755542
关键词
3-D deep learning; hyperspectral image classification; spectral-spatial feature extraction; spectral-spatial residual network (SSRN)
类别
资金
- China Scholarship Council
In this paper, we designed an end-to-end spectralspatial residual network (SSRN) that takes raw 3-D cubes as input data without feature engineering for hyperspectral image classification. In this network, the spectral and spatial residual blocks consecutively learn discriminative features from abundant spectral signatures and spatial contexts in hyperspectral imagery (HSI). The proposed SSRN is a supervised deep learning framework that alleviates the declining-accuracy phenomenon of other deep learning models. Specifically, the residual blocks connect every other 3-D convolutional layer through identity mapping, which facilitates the backpropagation of gradients. Furthermore, we impose batch normalization on every convolutional layer to regularize the learning process and improve the classification performance of trained models. Quantitative and qualitative results demonstrate that the SSRN achieved the state-of-the-art HSI classification accuracy in agricultural, rural-urban, and urban data sets: Indian Pines, Kennedy Space Center, and University of Pavia.
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