Unmanned Target Detection Based on Improved Faster-RCNN
There is still room to improve the performance of the original ReLU function of the Faster-RCNN backbone feature extraction network Resnet50.The use of Gaussian error linear element activation function GELU is explored to improve the perfor-mance of the original network.Compared with the relu activation function,the Gaussian error linear unit activation function GELU uses the probability method to retain the effective information,rather than the ReLU function,which simply retains the information greater than 0 and discards the information less than 0.This makes using GELU as the activation function can more accurately re-flect the image information,so as to improve the overall target detection performance of the network.Experiments show that com-pared with the original network,the map of the improved network has a certain improvement,has better performance in identifying road information,and can be better applied to driverless technology.
万方数据
维普
