Lightweight improvement research of DenseNet model
SHU Jun1,2， JIANG Mingwei1,2， YANG Li3， CHEN Yu3
1.School of Electrical and Electronic Engineering， Hubei University of Technology，Wuhan 430068， China；2.Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System， Hubei University of Technology， Wuhan 430068， China；3.School of Computer， Hubei University of Education， Wuhan 430205， China
Abstract：Aiming at the overfitting problem of deep DenseNet model on small-scale data sets， an improved lightweight DenseNet model is proposed in this paper. Firstly， we optimized the number of DenseBlock and its internal network structure. Then， an adaptive pooling layer method is proposed to solve the problem of adapting the resolution of the feature map of the new network. Finally， we added the SkipLayer to enhance the flow of feature information between DenseBlocks. The experimental results illustrated that the new method can reduced the parameter and calculation amount of the model， and solve the over-fitting problem of deep DenseNet effectively .
2020, Vol. 54 
