Nowadays,the design of convolutional neural network(CNN) models is getting deeper and *** traditional CNN is used to process limited data of remotesensing images,it will lead to *** will use lightweight and efficient...
详细信息
Nowadays,the design of convolutional neural network(CNN) models is getting deeper and *** traditional CNN is used to process limited data of remotesensing images,it will lead to *** will use lightweight and efficient models to classify remotesensing *** order to improve the classification accuracy and reduce the intermediate parameters,we improvedghostnet and proposed a smaller CNN named improved ***,we use image enhancement methods to enlarge the datasets and dropout,it will reduce the amount of *** experimented on three datasets,such as AID,UC Merced,***,we used MobileNetV3-Small and ghostnet to compare with our CNN *** classification accuracy of improvedghostnet achieves more than 91%,and the accuracy on the AID is improved by 2.05% compared to the original *** results demonstrate the effectiveness and efficiency of improvedghostnet.
暂无评论