In response to the challenges posed by convolutional neural network(CNNs)commonly used for hyperspectral image classification,namely,their high parameter count,extended training times,and sensitivity to sample quantity,a classification network MDSR&SE-Net based on improved squeeze and ex-citation network and depth-separable residuals was proposed for limited training samples.First,the prin-cipal component analysis is employed in this model to reduce the dimension of the original HSI.Then,the multi-feature residual structure is connected by 3D convolutional neural network,and the spatial &spec-tral details of hyperspectral images are extracted by embedding the improved squeeze and excitation block.Finally,the extracted feature information is input into Softmax classifier to activate classification.To fur-ther lightweight the network,the number of parameters is reduced by using the depth separable convolu-tion in the residual structure and introducing global average pooling.Experimental results show that over-all accuracy of the three common hyperspectral data sets with the limited training samples are above 99％.
关键词
高光谱图像/深度可分离卷积/残差网络/压缩激活网络
Key words
hyperspectral image/depth separable convolution/residual network/SE Net
维普
万方数据