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

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