Spectral-Spatial Attention Networks for Hyperspectral Image Classification
Spectral-Spatial Attention Networks for Hyperspectral Image Classification
复制标题
用于高光谱图像分类的光谱空间注意力网络
DOI：
10.3390/rs11080963
复制
发表时间：
2019-04-02
期刊：
影响因子：
5
通讯作者：
Ma, Jiayi
中科院分区：
文献类型：
--
作者：
Mei, Xiaoguang;Pan, Erting;Ma, Jiayi
许多深度学习模型，例如卷积神经网络（CNN）和循环神经网络（RNN），已成功应用于提取高光谱任务的深度特征。高光谱图像分类可以利用丰富的信息来区分土地覆盖的特征。受人类视觉系统注意机制的启发，在本研究中，我们提出了一种用于高光谱图像分类的光谱空间注意网络。在我们的方法中，具有注意力的 RNN 可以学习连续光谱内的内部光谱相关性，而具有注意力的 CNN 旨在关注空间维度中相邻像素之间的显着特征和空间相关性。实验结果表明，我们的方法可以充分利用光谱和空间信息来获得有竞争力的性能。
Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by the attention mechanism of the human visual system, in this study, we propose a spectral-spatial attention network for hyperspectral image classification. In our method, RNN with attention can learn inner spectral correlations within a continuous spectrum, while CNN with attention is designed to focus on saliency features and spatial relevance between neighboring pixels in the spatial dimension. Experimental results demonstrate that our method can fully utilize the spectral and spatial information to obtain competitive performance.