计算机应用与软件2016，Vol.33Issue(12)：165-168,4.DOI:10.3969/j.issn.1000-386x.2016.12.040
深度卷积神经网络在Caltech-101图像分类中的相关研究
RESEARCH ON DEEP CONVOLUTIONAL NEURAL NETWORK FOR CALTECH-101 IMAGE CLASSIFICATION
摘要
Abstract
At present,there are few studies about the effect of pre-training and fine tuning on the performance of convolutional neural network.Based on this,we proposed adopting CaffeNet network structure developed by Caffe framework and using convolutional neural network for image object recognition.In order to analyze the calculation process more intutively,we visualized the hidden layers’features in convolutional network.Through two experiments on Caltech-101 data sets,we analyzed the effects of randomly initialized model and pre-training model on the performance of deep convolutional classification as well as the effects of global fine tuning mode and local fine tuning mode on the performance of image classification.Experimental results showed that the pre-training model initialization can greatly improve the convergence speed and recognition accuracy,while the global fine tuning mode can fit the new sample data well and improve recognition accuracy as well.We achieved the mean recognition accuracy of 95.24% on Caltech-101 data sets and optimized the image recognition process more effectively.关键词
深度学习/卷积神经网络/图片分类/预训练/微调Key words
Deep learning/Convolution neural network/Image classification/Pre-training/Fine tuning分类
信息技术与安全科学引用本文复制引用
段建,翟慧敏..深度卷积神经网络在Caltech-101图像分类中的相关研究[J].计算机应用与软件,2016,33(12):165-168,4.基金项目
天津市教育信息化协会2015年度课题（15-01-405-0089）。 （）
