查询结果:   张占军,彭艳兵,程光.基于CIFAR-10的图像分类模型优化[J].计算机应用与软件,2018,35(3):177 - 181.
中文标题
基于CIFAR-10的图像分类模型优化
发表栏目
图像处理与应用
摘要点击数
921
英文标题
THE OPTIMIZATION OF IMAGE CATEGORIZATION MODEL BASED ON CIFAR-10
作 者
张占军 彭艳兵 程光 Zhang Zhanjun Peng Yanbing Cheng Guang
作者单位
武汉邮电科学研究院 湖北 武汉 430074 烽火通信科技股份有限公司南京研发 江苏 南京 210019    
英文单位
Wuhan Research Institute of Posts and Telecommunications,Wuhan 430074, Hubei, China Nanjing Research and Development Department, FiberHome Telecommunication Technologies Co.[KG-*3], Ltd.[KG-*3], Nanjing 210019, Jiangsu, China    
关键词
过拟合 数据增强 正则约束 卷积拆分 准确率
Keywords
Over-fitting Data enhancement Regular constraints Convolutional split Accuracy
基金项目
国家自然科学基金项目(61602114);国家高技术研究发展计划(2015AA015603)
作者资料
张占军,硕士生,主研领域:机器学习,分布式计算。彭艳兵,高工。程光,教授。 。
文章摘要
随着卷积神经网络在图像处理的研究与应用,图像的分类准确度得到了大幅提升,但是过拟合的问题却一直存在并成为影响分类准确率的重要因素。从过拟合的产生源头出发,增加数据量并减少参数数量以达到降低过拟合的目的。基于经典模型LeNet-5,对输入数据进行数据增强,并对卷积层进行拆分以减少参数,同时采用L1、L2混合约束的方法,并灵活调整两者的占比以达到最佳效果。实验结果表明,在CIFAR-10数据集上,优化后的网络达到了91.2%的准确率,相比最初的LeNet-5模型提高了23%,极大地降低了过拟合,提高了模型的分类准确率。
Abstract
With the research and application of convolutional neural network in image processing, the accuracy of image classification has been greatly improved, but the problem of over-fitting has always existed and has become an important factor affecting the classification accuracy. In this paper, starting from the source of over-fitting, we increased the amount of data and reduced the number of parameters in order to reduce the over-fitting purposes. Based on the classical model LeNet-5, this paper made input data enhancement and split the convolution layer to reduce the parameters. At the same time, it used L1 and L2 mixed constraints and adjusted the proportion of the two to achieve the best effect. Experimental results showed that the optimized network achieved 91.2% accuracy on the CIFAR-10 dataset. Compared with the original LeNet-5 model, it was increased by 23%. It greatly reduced the over-fitting, and improved the classification accuracy of the model.
下载PDF全文