基于GhostNet的改进模型轻量化方法  

Improved model lightweighting method based on GhostNet

作　　者：宋中山[1,2] 周珊 艾勇[1,2] 郑禄[1,2] 肖博文[1,2] SONG Zhongshan;ZHOU Shan;AI Yong;ZHENG Lu;XIAO Bowen(School of Computer Science,South-Central Minzu University,Wuhan 430074,China;Engineering Research Center for Intelligent Management of Manufacturing Enterprises,South-Central Minzu University,Wuhan 430074,China)

机构地区：[1]中南民族大学计算机科学学院,武汉430074 [2]中南民族大学湖北省制造企业智能管理工程技术中心,武汉430074

出　　处：《中南民族大学学报（自然科学版）》2024年第5期629-636,共8页Journal of South-Central University for Nationalities：Natural Science Edition

基　　金：湖北省科技重大专项资助项目(2020AEA011);武汉市科技计划应用基础前沿资助项目(2020020601012267);中央高校基本科研业务费专项资金资助项目(CZQ23040)。

摘　　要：为了降低深度卷积神经网络的部署成本,优化模型的检测性能,提出一种改进的轻量化主干网络算法S-GhostNet.该算法通过引入特征图生成优化的Ghost Module结构降低卷积操作的计算量,并结合改进类残差模块提升模型的精确度.S-GhostNet具有较强的即插即用性,可以应用于多数卷积神经网络模型.实验结果表明:在目标分类以及目标检测任务中,S-GhostNet相较于MobileNetV2、ShuffleNetV2以及GhostNet,模型计算量更小,模型的精确度持平,甚至更高.In order to reduce the deployment cost of deep convolutional neural networks and optimize the detection performance of the models,an improved lightweight backbone network algorithm S-GhostNet is proposed.The algorithm reduces the computational effort of convolutional operations by introducing a Ghost Module structure optimized for feature map generation.It improves the accuracy of the models by combining with an improved class of residual modules.S-GhostNet has a strong plug-and-play property and can be applied to most convolutional neural network models.Experimental results show that S-GhostNet is less computationally intensive than MobileNetV2,ShuffleNetV2 and GhostNet in target classification and target detection tasks.Also the accuracy of the model is similar or even higher.

关 键 词：目标检测 GhostNet网络 残差网络 轻量化部署 

分 类 号：S24[农业科学—农业电气化与自动化] TP2[农业科学—农业工程]