[1]高淑萍,赵清源,齐小刚,等.改进MobileNet的图像分类方法研究[J].智能系统学报,2021,16(1):11-20.[doi:10.11992/tis.202012034]
GAO Shuping,ZHAO Qingyuan,QI Xiaogang,et al.Research on the improved image classification method of MobileNet[J].CAAI Transactions on Intelligent Systems,2021,16(1):11-20.[doi:10.11992/tis.202012034]
点击复制
GAO Shuping,ZHAO Qingyuan,QI Xiaogang,et al.Research on the improved image classification method of MobileNet[J].CAAI Transactions on Intelligent Systems,2021,16(1):11-20.[doi:10.11992/tis.202012034]
改进MobileNet的图像分类方法研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
16
期数:
2021年第1期
页码:
11-20
栏目:
学术论文—机器学习
出版日期:
2021-01-05
- Title:
- Research on the improved image classification method of MobileNet
- Keywords:
- convolutional neural network; image classification; feature extraction; MobileNet; depth separable convolution; activation function; Leaky ReLU; residual structure
- 分类号:
- TP391;TP181
- 摘要:
- 针对神经网络结构的特征提取能力不足以及在包含复杂图像特征的数据集上分类准确率不高的问题，本文提出了一种对MobileNet神经网络的改进策略(L-MobileNet)。将原标准卷积形式替换为深度可分离卷积形式，并将深度卷积层得到的特征图执行取反操作，通过深度卷积融合层传递至下一层；采用Leaky ReLU激活函数代替原ReLU激活函数来保留图像中更多的正负特征信息，并加入类残差结构避免梯度弥散现象。与6种方法进行对比，实验结果表明：L-MobileNet在数据集Cifar-10、Cifar-100(coarse)、Cifar-100(fine)和Dogs vs Cats上平均准确率和最高准确率都取得了最佳结果。
- Abstract:
- This paper proposes an improved strategy for the MobileNet neural network (L-MobileNet) because the feature extraction ability of a neural network structure is insufficient, and the classification accuracy is not high on the dataset containing complex image features. First, the original standard convolution form is replaced by the depth separable convolution form, and the feature map obtained from the deep convolution layer is reversed and transferred to the next layer through the deep convolution fusion layer. Second, the leaky ReLU activation function is used to replace the original ReLU activation function to retain more positive and negative feature information in the image, and residual structure is added to avoid the gradient diffusion phenomenon. Finally, the experimental results showed that when compared with six methods, L-MobileNet achieved the best results in the datasets of Cifar-10, Cifar-100 (coarse), Cifar-100 (fine), and Dogs vs Cats.
- 参考文献/References:
-
[1] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[2] SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with con-volutions[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015:1-9.
[3] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016:770-778.
[4] HAN K, WANG Y, TIAN Q, et al. GhostNet:More features from cheap operations[J]. arXiv preprint arXiv:1911.11907, 2019.
[5] ZHANG X, ZHOU X, LIN M, et al. Shufflenet:an extremely efficient convolutional neural network for mobile devic-es[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:6848-6856.
[6] HOWARD A G, ZHU Menglong, CHEN Bo, et al. MobileNets:efficient convolutional neural networks for mobile vision applications[J]. arXiv:1704.04861, 2017.
[7] SANDLER M, HOWARD A, ZHU Menglong, et al. MobileNetv2:inverted residuals and linear bottlenecks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:4510-4520.
[8] MA Ningning, ZHANG Xiangyu, ZHENG Haitao, et al. ShuffleNet V2:practical guidelines for efficient CNN architecture design[C]//Proceedings of the 15th European Conference on Computer Vision. Munich, Germany, 2018:116-131.
[9] IANDOLA F N, HAN Song, MOSKEWICZ M W, et al. SqueezeNet:AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size[J]. arXiv:1602.07360, 2016.
[10] SUN Ke, LI Mingjie, LIU Dong, et al. IGCV3:interleaved low-rank group convolutions for efficient deep neural networks[J]. arXiv:1806.00178, 2018.
[11] 黄跃珍, 王乃洲, 梁添才, 等. 基于改进型MobileNet网络的车型识别方法[J]. 电子技术与软件工程, 2019(1):22-24
HUANG Yuezhen, WANG Naizhou, LIANG Tiancai, et al. Vehicle identification method based on improved mobilenet network[J]. Electronic technology and software engineering, 2019(1):22-24
[12] 刘鸿智. 面向移动设备的轻型神经网络的改进与实现[D]. 呼和浩特:内蒙古大学, 2019.
LIU Hongzhi. Improvement and implementation of lightweight neural network for mobile devices[D]. Hohhot:Inner Mongolia University, 2019.
[13] 郭奕君, 努尔毕亚·亚地卡尔, 朱亚俐, 等. 基于MobileNet网络多国人脸分类识别[J]. 图像与信号处理, 2020, 9(3):146-155.GUO Yijun, ABUDIRIYIMU A, YADIKAR N, et al. Multinational face classification and recognition based on MobileNet network[J]. Journal of image and signal processing, 2020, 9(3):146-155.
[14] DUBEY A K, JAIN V. Comparative study of convolution neural network’s relu and leaky-relu activation functions[M]. MISHRA S, SOOD Y R, TOMAR A. Applications of Computing, Automation and Wireless Systems in Electrical Engineering. Singapore:Springer, 2019:873-880.
[15] CHEN Yinpeng, DAI Xiyang, LIU Mengchen, et al. Dynamic ReLU[J]. arXiv:2003.10027, 2020.
[16] KRIZHEVSKY A. Learning multiple layers of features from tiny images[R]. Toronto:University of Toronto, 2009.
[17] DUGAN P, CUKIERSKI W, SHIU Y, et al. Kaggle competition[J]. Cornell University, the ICML, 2013.
[18] XU Bing, WANG Naiyan, CHEN Tianqi, et al. Empirical evaluation of rectified activations in convolutional network[J]. arXiv:1505.00853, 2015.
[19] RANZATO M A, HINTON G E. Modeling pixel means and covariances using factorized third-order Boltzmann machines[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010:2551-2558.
[20] YU Kai, ZHANG Tong. Improved local coordinate Coding using local tangents[C]//Proceedings of the 27th International Conference on Machine Learning. Haifa, Israel, 2010.
[21] CHAN T H, JIA Kui, GAO Shenghua, et al. PCANet:a simple deep learning baseline for image classification?[J]. IEEE transactions on image processing, 2015, 24(12):5017-5032.
[22] ZEILER M D, FERGUS R. Stochastic pooling for regularization of deep convolutional neural networks[J]. arXiv:1301.3557, 2013.
[23] 刘金利, 张培玲. 改进LeNet-5网络在图像分类中的应用[J]. 计算机工程与应用, 2019, 55(15):32-37, 95.
LIU Jinli, ZHANG Peiling. Application of improved LeNet-5 network in image classification[J]. Computer engineering and applications, 2019 (15):5.
[24] GOODFELLOW I J, WARDE FARLEY D, MIRZA M, et al. Maxout networks[J]. arXiv preprint arXiv:1302.4389, 2013.
[25] LIN Min, CHEN Qiang, YAN Shuicheng. Network in network[J]. arXiv:1312.4400, 2013.
[26] SRIVASTAVA R K, GREFF K, SCHMIDHUBER J. Highway networks[J]. arXiv:1505.00387, 2015.
- 相似文献/References:
-
[1]李海峰,杜军平.颜色特征的图像分类技术研究[J].智能系统学报,2008,3(2):65.[doi:CNKI:SUN:ZNXT.0.2008-02-017]
[2]李海峰,杜军平.颜色特征的图像分类技术研究[J].智能系统学报,2008,3(2):155.
LI Hai-feng,DU Jun-ping.Image classification technology based on color features[J].CAAI Transactions on Intelligent Systems,2008,3():155.
[3]姚伏天,钱沄涛.高斯过程及其在高光谱图像分类中的应用[J].智能系统学报,2011,6(5):396.
YAO Futian,QIAN Yuntao.Gaussian process and its applications in hyperspectral image classification[J].CAAI Transactions on Intelligent Systems,2011,6():396.
[4]尤雅萍,成运,苏松志,等.基于谱域-空域结合特征和图割原理的高光谱图像分类[J].智能系统学报,2015,10(2):201.[doi:10.3969/j.issn.1673-4785.201410040]
YOU Yaping,CHENG Yun,SU Songzhi,et al.Hyperspectral image classification based on spectral-spatial combination features and graph cut[J].CAAI Transactions on Intelligent Systems,2015,10():201.[doi:10.3969/j.issn.1673-4785.201410040]
[5]殷瑞,苏松志,李绍滋.一种卷积神经网络的图像矩正则化策略[J].智能系统学报,2016,11(1):43.[doi:10.11992/tis.201509018]
YIN Rui,SU Songzhi,LI Shaozi.Convolutional neural network’s image moment regularizing strategy[J].CAAI Transactions on Intelligent Systems,2016,11():43.[doi:10.11992/tis.201509018]
[6]龚震霆,陈光喜,任夏荔,等.基于卷积神经网络和哈希编码的图像检索方法[J].智能系统学报,2016,11(3):391.[doi:10.11992/tis.201603028]
GONG Zhenting,CHEN Guangxi,REN Xiali,et al.An image retrieval method based on a convolutional neural network and hash coding[J].CAAI Transactions on Intelligent Systems,2016,11():391.[doi:10.11992/tis.201603028]
[7]刘帅师,程曦,郭文燕,等.深度学习方法研究新进展[J].智能系统学报,2016,11(5):567.[doi:10.11992/tis.201511028]
LIU Shuaishi,CHENG Xi,GUO Wenyan,et al.Progress report on new research in deep learning[J].CAAI Transactions on Intelligent Systems,2016,11():567.[doi:10.11992/tis.201511028]
[8]师亚亭,李卫军,宁欣,等.基于嘴巴状态约束的人脸特征点定位算法[J].智能系统学报,2016,11(5):578.[doi:10.11992/tis.201602006]
SHI Yating,LI Weijun,NING Xin,et al.A facial feature point locating algorithmbased on mouth-state constraints[J].CAAI Transactions on Intelligent Systems,2016,11():578.[doi:10.11992/tis.201602006]
[9]赵骞,李敏,赵晓杰,等.基于感受野学习的特征词袋模型简化算法[J].智能系统学报,2016,11(5):663.[doi:10.11992/tis.201601001]
ZHAO Qian,LI Min,ZHAO Xiaojie,et al.Learning receptive fields for compact bag-of-feature model[J].CAAI Transactions on Intelligent Systems,2016,11():663.[doi:10.11992/tis.201601001]
[10]费宇杰,吴小俊.一种局部聚合描述符和组显著编码相结合的编码方法[J].智能系统学报,2017,12(2):172.[doi:10.11992/tis.201602010]
FEI Yujie,WU Xiaojun.A new feature coding algorithm based on the combination of group salient coding and VLAD[J].CAAI Transactions on Intelligent Systems,2017,12():172.[doi:10.11992/tis.201602010]
[11]赵玉新,赵廷.海底声呐图像智能底质分类技术研究综述[J].智能系统学报,2020,15(3):587.[doi:10.11992/tis.202004026]
ZHAO Yuxin,ZHAO Ting.Survey of the intelligent seabed sediment classification technology based on sonar images[J].CAAI Transactions on Intelligent Systems,2020,15():587.[doi:10.11992/tis.202004026]
[12]郭磊,王骏,丁维昌,等.4D卷积神经网络的自闭症功能磁共振图像分类[J].智能系统学报,2021,16(6):1021.[doi:10.11992/tis.202009022]
GUO Lei,WANG Jun,DING Weichang,et al.Classification of the functional magnetic resonance image of autism based on 4D convolutional neural network[J].CAAI Transactions on Intelligent Systems,2021,16():1021.[doi:10.11992/tis.202009022]
[13]刘嘉轩,胡非易,张辉,等.上下文空间与实例信息的皮肤镜图像自监督分类[J].智能系统学报,2023,18(4):783.[doi:10.11992/tis.202211010]
LIU Jiaxuan,HU Feiyi,ZHANG Hui,et al.Dermoscopic images classification based on context and instance-level feature of self-supervised learning[J].CAAI Transactions on Intelligent Systems,2023,18():783.[doi:10.11992/tis.202211010]
[14]陈容珊,高淑萍,齐小刚.注意力机制和图卷积神经网络引导的谱聚类方法[J].智能系统学报,2023,18(5):936.[doi:10.11992/tis.202208041]
CHEN Rongshan,GAO Shuping,QI Xiaogang.A spectral clustering based on GCNs and attention mechanism[J].CAAI Transactions on Intelligent Systems,2023,18():936.[doi:10.11992/tis.202208041]
[15]莫宏伟,孙琪,孙鹏,等.乳腺钼靶肿块自监督预训练迁移检测方法研究[J].智能系统学报,2024,19(5):1082.[doi:10.11992/tis.202304032]
MO Hongwei,SUN Qi,SUN Peng,et al.Self-supervised pretraining detection of mammographic mass targets in breast[J].CAAI Transactions on Intelligent Systems,2024,19():1082.[doi:10.11992/tis.202304032]
备注/Memo
收稿日期:2020-12-31。
基金项目:国家自然科学基金项目(91338115)；高等学校学科创新引智基地“111”计划(B08038)
作者简介:高淑萍，教授，主要研究方向为多目标优化理论与应用、数学与信息科学交叉研究、大数据处理与分析。主持、参与国家级和省自然科学基金项目及横向项目多项。发表学术论文30余篇;赵清源，硕士研究生，主要研究方向为深度学习、图像分类、算法优化;齐小刚，教授，博士生导师，主要研究方向为复杂系统建模与仿真、网络算法设计与应用。申请专利47项(授权19项)，登记软件著作权4项。发表学术论文100余篇
通讯作者:赵清源. E-mail：zqy353364144@163.com
更新日期/Last Update:
2021-02-25