• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 论文 • 上一篇    下一篇

基于残差的优化卷积神经网络服装分类算法

张振焕,周彩兰,梁媛   

  1. (武汉理工大学计算机学院,湖北  武汉 430070)
  • 收稿日期:2017-08-01 修回日期:2017-10-05 出版日期:2018-02-25 发布日期:2018-02-25

An optimized clothing classification algorithm
based on residual convolutional neural network
 

ZHANG Zhen-huan,ZHOU Cai-lan,LIANG Yuan   

  1. (School of Computer Science,Wuhan University of Technology,Wuhan 430070,China)
  • Received:2017-08-01 Revised:2017-10-05 Online:2018-02-25 Published:2018-02-25

摘要:

针对目前服装分类算法在解决多类别服装分类问题时分类精度一般的问题,提出了一种基于残差的优化卷积神经网络服装分类算法,在网络中使用了如下三种优化方法:(1)调整批量归一化层、激活函数层与卷积层在网络中的排列顺序;(2)“池化层+卷积层”的并行池化结构;(3)使用全局均值池化层替换全连接层。经过由香港中文大学多媒体实验室提供的多类别大型服装数据集(DeepFashion)和标准数据集CIFAR-10上的实验表明,所提出的网络模型在处理图片的速度和分类精度方面都优于VGGNet和AlexNet,且得到了目前为止已知的在DeepFashion数据集上最好的分类准确率。该网络也可以更好地应用于目标检测和图像分割领域。

 

关键词: 深度学习, 残差网络, 多类别服装分类, 卷积神经网络优化

Abstract:

Aiming at the problem that the current clothing classification algorithm has general accuracy in solving the multi-category clothing classification, this paper proposes an optimized clothing classification algorithm based on residual convolutional neural network, and uses the following three optimization methods in the network: 1) The orders of batch normalized layer (BN), activation function (Relu) and convolution layer in the network are adjusted; 2) A parallel pooling structure of "pool layer + convoluted layer" is adopted; 3) The full connection layer is replaced by the global mean pooling layer. Experiments on the multi-category large-scale clothing data set (DeepFashion) provided by the multimedia laboratory, the Chinese university of Hong Kong and the standard data set CIFAR-10 show that the proposed network model is superior to VGGNet and AlexNet in image processing speed and classification accuracy, and obtains the best classification accuracy on DeepFashion data set so far. The network can also be better applied to target detection and image segmentation.
 

Key words: deep learning, residual network, multiple categories clothing classification, convolution neural network optimization