Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (16): 179-184.DOI: 10.3778/j.issn.1002-8331.1805-0289

Previous Articles     Next Articles

Joint Structure Similarity and Class Information for Image Classification

XIONG Wei, LIU Hao, WANG Yuejingyan, WANG Juan, ZENG Chunyan, ZHANG Fan   

  1. 1.School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China
    2.Hubei Collaborative Innovation Center for High-Efficiency Utilization of Solar Energy, Wuhan 430068, China
  • Online:2019-08-15 Published:2019-08-13

联合结构相似性与类信息的图像分类

熊炜,刘豪,王玥婧妍,王娟,曾春艳,张凡   

  1. 1.湖北工业大学 电气与电子工程学院,武汉 430068
    2.太阳能高效利用湖北省协同创新中心,武汉 430068

Abstract: A kind of weighted joint structure similarity and class information method is proposed for the problem of slow convergence of convolutional neural network training. Firstly, this paper designs a convolutional neural network which can effectively extract high-level information for small images. Secondly, this paper constructs a weighted joint structure similarity and class information loss function to train convolutional neural networks. Finally, the effectiveness of the designed network structure is verified by mnist handwritten numeral and cifar10 image classification experiments. The experimental results show that the error rate of image classification on mnist handwritten and cifar10 datasets are 0.33% and 11% by using the designed network, respectively. In the case of no data argumentation on the mnist dataset, the performance of the designed network is much better than all single networks. On the cifar10 dataset, the designed network can achieve higher image classification accuracy with less computation. At the same time, joint structure similarity and class information loss can speed up the network training process.

Key words: convolutional neural network, image classification, structure similarity, deep learning, metric learning

摘要: 针对卷积神经网络训练收敛速度慢的问题,提出了一种加权的联合结构相似性和类信息监督训练的方法。首先,针对小图像,设计一个能有效提取图像高级别信息的卷积神经网络。其次,建立加权的联合结构相似性和类信息损失函数训练卷积神经网络。最后,通过mnist手写数字和cifar10图像分类实验验证所设计网络的有效性。实验结果表明,所设计的网络在mnist手写数字和cifar10数据集上的图像分类错误率分别为0.33%和11%。在未进行扩增mnist数据集的前提下,所设计的网络的性能超过了该数据集上所有单网络的性能;在cifar10数据集上,所设计的网络能以较少的计算量获得较高的图像分类准确率。同时,联合结构相似性和类信息损失的监督训练能加快网络的训练速度。

关键词: 卷积神经网络, 图像分类, 结构相似性, 深度学习, 度量学习