Research of Lightweight Convolution Neural Network Based on Feature Expansion Convolution

This paper starts with the network structure of convolution neural network model, and uses the idea of fea⁃ ture reuse to design an efficient feature expansion convolution module. The module reduces the number of output channels of standard convolution module and introduces multi branch structure. Through the cheap operation on each branch, the out⁃ put feature map of standard convolution operation is transformed and fused to generate a new feature map. The final output of the module is obtained by merging the feature graphs generated on each branch. The feature expansion convolution mod⁃ ule uses the idea of feature reuse to reuse the features in the model, which not only reduces the calculation of the model, but also enriches the hidden information of the feature graph and improves the performance of the model. Finally, the feature ex⁃ pansion convolution module is used to replace the standard convolution module, and the lightweight VGG16 (Visual Geom⁃ etry Group 16-Layer) model and residual structure are designed, and good classification results are achieved on CIFAR and ILSVRC2012 (ImageNet Large Scale Visual Recognition Challenge 2012) datasets. © 2023 Chinese Institute of Electronics. All rights reserved.