基于低开销可变形卷积的MobileNet再轻量化方法  

Re-lightweight Method of MobileNet Based on Low-cost Deformable Convolution

作　　者：孙长迪 潘志松 张艳艳 SUN Chang-di;PAN Zhi-song;ZHANG Yan-yan(College of Command and Control Engineering,Army Engineering University of PLA,Nanjing 210007,China)

机构地区：[1]陆军工程大学指挥控制工程学院,南京210007

出　　处：《计算机科学》2022年第12期312-318,共7页Computer Science

基　　金：国家自然科学基金(62076251)。

摘　　要：近年来,随着无人驾驶、无人机智能化、移动互联网的发展,低功耗、低算力的移动和嵌入式平台对轻量化的神经网络需求日益迫切。文中基于可变形卷积和深度可分离卷积思想的启发,提出了一种低开销可变形卷积,其兼具了可变形卷积的高效特征提取能力和深度可分离卷积的低运算量的优点。此外,在应用低开销可变形卷积的基础上,结合模型结构压缩的方法,设计了4种MobileNet网络再轻量化的方法。在Caltech256,CIFAR100和CIFAR10数据集上进行了实验,结果表明,低开销可变形卷积在运算量增加不明显的情况下,可以有效提高轻量级网络的分类准确度。并且,结合所提出的4种MobileNet再轻量化方法,可以将MobileNet网络的准确度提高0.4%~1%,与此同时网络运算量可以下降5%~15%,即显著提高了轻量化网络的各项性能,更加符合低功耗、低算力的现实需求,对于移动和嵌入式平台领域的智能化推进有着很重要的现实意义。In recent years,with the development of unmanned driving,intelligent UAV and mobile Internet,the demand for lightweight neural network from low-power,low-cost mobile and embedded platforms is increasingly urgent.Based on the idea of deformable convolution and depthwise separable convolution,this paper presents a low-cost deformable convolution,which has the advantages of high-efficiency feature extraction ability of deformable convolution and low computational complexity of depthwise separable convolution.In addition,on the basis of applying low-cost deformable convolution and combining with the method of model structure compression,4 lightweight methods of MobileNet network are designed.Experiments on Caltech256,CIFAR100 and CIFAR10 datasets demonstrate that low-cost deformable convolution can effectively improve the classification accuracy of lightweight networks without significant increase in computational effort.Besides,the accuracy of the MobileNet network can be improved by 0.4%~1%by combining the 4 MobileNet re-lightening methods in this paper,while the network computing load can be reduced by 5%~15%,which significantly improves the performance of the lightweight network and better meets the practical needs of low power consumption and low computing power.It has very important practical significance for the advancement of intelligence in the field of mobile and embedded platforms.

关 键 词：低开销可变形卷积 可变形卷积 深度可分离卷积 MobileNet 轻量化 图像分类 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]