###
计算机系统应用:2018,27(8):35-41
本文二维码信息
码上扫一扫!
基于残差量化卷积神经网络的人脸识别方法
周光朕1, 杜姗姗2, 冯瑞1,2, 欧丽君3, 刘斌4
(1.复旦大学 计算机科学技术学院, 上海 201203;2.上海市智能信息处理重点实验室 上海视频技术与系统工程研究中心, 上海 201203;3.上海临港智慧城市发展中心, 上海 201306;4.上海无线电设备研究所, 上海 200090)
Face Recognition Method Based on Quantized Residual Convolutional Neural Networks
ZHOU Guang-Zhen1, DU Shan-Shan2, FENG Rui1,2, OU Li-Jun3, LIU Bin4
(1.School of Computer Science, Fudan University, Shanghai 201203, China;2.Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Engineering Research Center for Video Technology and System, Shanghai 201203, China;3.Shanghai Lingang Smart City Development Center, Shanghai 201306, China;4.Shanghai Radio Equipment Research Institute, Shanghai 200090, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 143次   下载 152
投稿时间:2018-01-02    修订日期:2018-01-23
中文摘要: 针对大规模人脸识别问题,基于残差学习的超深卷积神经网络模型能取得比其他方法更高的识别精度,然而模型中存在的海量浮点参数需要占用大量的计算和存储资源,法满足资源受限的场合需求.针对这一问题,本文设计了一种基于网络参数量化的超深残差网络模型.具体在Face-ResNet模型的基础上,增加了批归一化层和dropout层,加深了网络层次,对网络模型参数进行了二值量化,在模型识别精度损失极小的情况下,大幅压缩了模型大小并提升了计算效率.通过理论分析与实验验证了本文设计方法的有效性.
Abstract:Very deep convolutional neural networks based on residual learning have achieved higher accuracy than other methods for large scale face recognition problem. But the massive floating-point parameters existing in the models need to occupy extensive computational and memory resources, which cannot be satisfied with the demand of occasions with limited resources. Aimed at the solution of this issue, a very deep residual neural network based on network model parameters quantization was designed in this study. In detail, based on the model Face-ResNet, the network was added with batch normalization layers and dropout layers, and also its total layers were deepened. Applying binary quantization to parameters of the designed network models, it can compress the model size substantially and improve computational efficiency with little loss of model recognition accuracy. Both theoretical analysis and experiments prove the effectiveness of the designed method.
文章编号:     中图分类号:    文献标志码:
基金项目:国家重点研发计划(2017YFC0803700);上海市科委项目(17511101702);临港地区智能制造产业专项(#ZN2016020103);复旦大学工程与应用技术研究院先导项目(gyy2017-003)
引用文本:
周光朕,杜姗姗,冯瑞,欧丽君,刘斌.基于残差量化卷积神经网络的人脸识别方法.计算机系统应用,2018,27(8):35-41
ZHOU Guang-Zhen,DU Shan-Shan,FENG Rui,OU Li-Jun,LIU Bin.Face Recognition Method Based on Quantized Residual Convolutional Neural Networks.COMPUTER SYSTEMS APPLICATIONS,2018,27(8):35-41

用微信扫一扫

用微信扫一扫