基于改进胶囊神经网络的遥感影像分类

Remote Sensing Image Classification Based on Advanced Capsule Neural Network

针对遥感影像卷积神经网络(CNN)分类会导致特征信息丢失及泛化能力差的问题,提出一种基于通道注意力和混合注意力改进的胶囊神经网络分类模型。首先,为了胶囊神经网络能够适应于大尺寸输入图像,在特征提取模块中使用2个最大池化层;其次,为了提高分类精度,分别将SENet注意力和CBAM注意力加在特征提取模块的最后一层去改进特征提取模块;最后,将样本集随机地划分为训练集、验证集和测试集,进一步使用训练集和验证集训练模型,测试集测试模型,使用AID数据集对模型分类的泛化能力进行验证。实验结果表明:基于SENet网络改进的胶囊神经网络的准确率与Kappa系数要高于其他模型,泛化能力也优于其他模型,本文提出的模型的总体分类精度和泛化能力有了显著性提升,从而验证了本文方法的可行性和使用性。

Aiming at the problems of feature information loss and poor generalization ability caused by convolutional neural network(CNN)classification of remote sensing image,an improved capsule neural network classification model based on channel attention and mixed attention is proposed.Firstly,in order for the capsule neural network to adapt to large-size input images,the two maximum pooling layers are used in the feature extraction module.Secondly,in order to improve the classification accuracy,the SENet attention and CBAM attention are added to the last layer of the feature extraction module for improving the feature extraction module.Finally,the sample set is randomly divided into training set,verification set and test set,and the training set and veritication set are further used to train the model,the test set to test the model,and the AID data set is used to verity the generalization ability of model classification.The experimental results show that the accuracy and Kappa coefficient of the improved capsule neural network based on the SENet network are higher than other models,and the generalization ability is also.The overall classification accuracy and generalization ability of the proposed model are significant improved,thus verifying the feasibility and usability of the method.