Abstract:
Complex-valued convolutional neural network (CV-CNN) has been presented in recent years. In this letter, CV full convolutional neural network (CV-FCNN) is proposed for sy...Show MoreMetadata
Abstract:
Complex-valued convolutional neural network (CV-CNN) has been presented in recent years. In this letter, CV full convolutional neural network (CV-FCNN) is proposed for synthetic aperture radar (SAR) target classification, which contains only convolution layers in the hidden layer. The purpose of replacing both the pooling and fully connected layers in CV-CNN with the convolution layers is to avoid complex pooling operation and prevent overfitting, respectively. Considering the label of target is always real-valued, the magnitude of the complex vector obtained from the last convolution layer is calculated before softmax classification in the output layer. Moreover, the back-propagation formula for each layer of CV-FCNN is presented in detail. Furthermore, the complex 1\times 1 convolution layer is added into CV-FCNN to learn the cross-channel information of feature maps. The experimental results show that the average accuracy can be improved using CV-FCNN, and it is further improved using CV-FCNN with the 1\times 1 convolution layer.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 17, Issue: 10, October 2020)