一种新的高效轻量级卷积神经网络模型

摘要/Abstract

摘要： 针对目前食物识别系统中网络模型参数量多、模型较大的问题，提出一种23层结构、参数量只有204k的网络模型，使用基本构造块（7×7、5×5、3×3）生成特征图，用不同感受野的2个池化层来融合卷积层的特征图，再用1×1的卷积核进行非线性组合，然后连接到空间金字塔池化层，最后在softmax分类器中分类。在公开数据集上的实验表明，与ResNet50和GoogLeNet相比，本文网络模型在分类性能不降低的情况下，模型参数分别减少了99.14%和96.63%。

关键词: 卷积神经网络, 深度学习, 食物分类, 空间金字塔池化

Abstract: Aiming at the problem that the current food recognition system has a large number of network model parameters and a large model, this paper proposes a 23-layer network model with only 204k parameters. The basic building blocks (7×7, 5×5, 3×3) are used to generate feature maps, and two pooling layers of different receptive fields are used to fuse the feature map of the convolutional layer, and a 1×1 convolution kernel is used for nonlinear combination. Then it is connected to the spatial pyramid pooling layer, and finally is classified in the softmax classifier. Experiments on public data sets show that, compared with ResNet50 and GoogLeNet, the network model in this paper reduces model parameters by 99.14% and 96.63% respectively without reducing classification performance.

Key words: convolutional neural network, deep learning, food classification, spatial pyramid pooling

张舰舰. 一种新的高效轻量级卷积神经网络模型[J]. 计算机与现代化, 2021, 0(04): 98-103.

ZHANG Jian-jian. A New Efficient and Lightweight Convolutional Neural Network Model[J]. Computer and Modernization, 2021, 0(04): 98-103.

参考文献［27］

［1］	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks［C］// Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012:1097-1105.
［2］	SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions［C］// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015:1-9.
［3］	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:770-778.
［4］	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition［J］. arXiv preprint arXiv:1409.1556, 2014.
［5］	KONG F Y, TAN J D. DietCam: Regular shape food recognition with a camera phone［C］// Proceedings of the 2011 International Conference on Body Sensor Networks. 2011:127-132.
［6］	KAWANO Y, YANAI K. Real-time mobile food recognition system［C］// Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2013:1-7.
［7］	ANTHIMOPOULOS M, GIANOLA L, SCARNATO L, et al. A food recognition system for diabetic patients based on an optimized bag-of-features model［J］. IEEE Journal of Biomedical and Health Informatics, 2014,18(4):1261-1271.
［8］	ANTHIMOPOULOS M, DEHAIS J, DIEM P, et al. Segmentation and recognition of multi-food meal images for carbohydrate counting［C］// Proceedings of the 13th IEEE International Conference on BioInformatics and BioEngineering. 2013. DOI: 10.1109/BIBE.2013.6701608.
［9］	MATSUDA Y, YANAI K. Multiple-food recognition considering co-occurrence employing manifold ranking［C］// Proceedings of the 2012 21st International Conference on Pattern Recognition. 2012:2017-2020.
［10］	HE H S, KONG F Y, TAN J D. DietCam: Multiview food recognition using a multikernel SVM［J］. IEEE Journal of Biomedical and Health Informatics, 2016,20(3):848-855.
［11］	DUAN P C, WANG W S, ZHANG W S, et al. Food image recognition using pervasive cloud computing［C］// Proceedings of the 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing. 2013:1631-1637.
［12］	ZHANG W S, ZHAO D H, GONG W J, et al. Food image recognition with convolutional neural networks［C］// Proceedings of the 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing and 2015 IEEE 12th International Conference on Autonomic and Trusted Computing and 2015 IEEE 15th International Conference on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom). 2015:690-693.
［13］	WANG X, KUMAR D, THOME N, et al. Recipe recognition with large multimodal food dataset［C］// Proceedings of the 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). 2015. DOI: 10.1109/ICMEW.2015.7169757.
［14］	KAWANO Y, SATO T, MARUYAMA T, et al. ［Demo paper］ Mirurecipe: A mobile cooking recipe recommendation system with food ingredient recognition［C］// Proceedings of the 2013 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). 2013. DOI: 10.1109/ICMEW.2013.6618222.
［15］	XU R H, HERRANZ L, JIANG S Q, et al. Geolocalized modeling for dish recognition［J］. IEEE Transactions on Multimedia, 2015,17(8):1187-1199.
［16］	HASSANNEJAD H, MATRELLA G, CIAMPOLINI P, et al. Food image recognition using very deep convolutional networks［C］// Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management. 2016:41-49.
［17］	SERMANET P, LECUN Y. Traffic sign recognition with multi-scale convolutional networks［C］// Proceedings of the 2011 International Joint Conference on Neural Networks. 2011:2809-2813.
［18］	MAAS A L, HANNUN A Y, NG A Y. Rectifier nonlinearities improve neural network acoustic models［C］// Proceedings of the 2013 ICML Workshop on Deep Learning for Audio, Speech and Language Processing. 2013.
［19］	HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: Surpassing human-level performance on imageNet classification［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). 2015:1026-1034.
［20］	HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015,37(9):1904-1916.
［21］	IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift［C］// Proceedings of the 32nd International Conference on Machine Learning. 2015:448-456.
［22］	CLEVERT D, UNTERTHINER T, HOCHREITER S. Fast and accurate deep network learning by exponential linear units (ELUs)［J］. arXiv preprint arXiv:1511.07289, 2015.
［23］	BOSSARD L, GUILLAUMIN M, VAN GOOL L. Food-101: Mining discriminative components with random forests［C］// Proceedings of the 2014 European Conference on Computer Vision. 2014:446-461.
［24］	LIU Z, YAN W Q, YANG M L. Image denoising based on a CNN model［C］// Proceedings of the 2018 4th International Conference on Control, Automation and Robotics (ICCAR). 2018:389-393.
［25］	DOSOVITSKIY A, BROX T. Inverting visual representations with convolutional networks［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:4829-4837.
［26］	MAHENDRAN A, VEDALDI A. Understanding deep image representations by inverting them［C］// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015:5188-5196.
［27］	KAWANO Y, YANAI K. Automatic expansion of a food image dataset leveraging existing categories with domain adaptation［C］// Proceedings of the 2014 European Conference on Computer Vision. 2014:3-17.

[1]	胡崇佳, 刘金洲, 方立. 基于无监督域适应的室外点云语义分割[J]. 计算机与现代化, 2024, 0(01): 74-79.
[2]	林威. 基于自监督学习和数据回放的新闻推荐模型增量学习方法[J]. 计算机与现代化, 2023, 0(12): 1-6.
[3]	周成诚, 曾庆军, 杨康, 胡家铭, 韩春伟. 基于高效通道注意力模块的运动想象脑电识别[J]. 计算机与现代化, 2023, 0(12): 19-23.
[4]	梁天恺, 黄康华, 刘凯航, 兰岚, 曾碧. 基于双向同态加密的深度联邦图片分类方法[J]. 计算机与现代化, 2023, 0(12): 36-40.
[5]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[6]	张伯泉, 麦海鹏, 陈嘉敏, 逄锦聚. 基于高灰度值注意力机制的脑白质高信号分割[J]. 计算机与现代化, 2023, 0(12): 67-75.
[7]	马泽宇, 叶宁, 徐康, 王甦, 王汝传, . 基于FMCW雷达和ResNeSt-GRU的行为识别方法[J]. 计算机与现代化, 2023, 0(11): 101-107.
[8]	李延满, 王必恒, 赵羚焱. 基于轻量化YOLOv5的安全帽检测[J]. 计算机与现代化, 2023, 0(10): 59-64.
[9]	黎世达, 项剑文. 一种提高图像识别模型鲁棒性的弱化强化方法[J]. 计算机与现代化, 2023, 0(10): 70-76.
[10]	沈加炜, 陆一鸣, 陈晓艺, 钱美玲, 陆卫忠, . 基于深度学习的人体行为检测方法研究综述[J]. 计算机与现代化, 2023, 0(09): 1-9.
[11]	刘付琪, 张达, 宋建华, 王海东. 基于CNN-BiLSTM的液压系统故障诊断[J]. 计算机与现代化, 2023, 0(09): 10-19.
[12]	吴甜, 刘海华, 童顺延. 基于深度反馈的卷积神经网络的图像分类[J]. 计算机与现代化, 2023, 0(09): 82-86.
[13]	刘禅奕, 黄丹, 薛林雁, 王涛, 朱桃, . 改进EfficientNet网络的COVID-19 X光分类[J]. 计算机与现代化, 2023, 0(09): 94-99.
[14]	马国祥, 杨凌菲, 严传波, 张志豪, 孙彬, 王晓荣. 基于深度DenseNet网络的肝包虫病超声影像诊断方法[J]. 计算机与现代化, 2023, 0(09): 100-104.
[15]	陈嘉敏, 张伯泉, 麦海鹏. 基于特征融合的海马体分割[J]. 计算机与现代化, 2023, 0(08): 1-6.