量型图像分类神经网络改进研究

当前普遍使用的轻量型神经网络仍然存在计算量与参数量过大的问题,导致算力较低的廉价移动设备无法快速完成图像分类任务.针对此问题提出了一种更适合于应用在算力较低的廉价移动设备上的轻量型神经网络,引入了代价较小的线性操作与特征图合并操作用于减少神经网络的计算量与参数量,还引入了改进的残差结构、注意力机制和标签平滑技术用于提高结果判断的准确率.基于PD-38数据集的实验表明,该神经网络相比传统的轻量型神经网络使用较小的计算量与参数量可以达到较高的分类准确率.在公共数据集CIFAR-10上的实验进一步表明该神经网络具有通用性.

Research on improvement of lightweight image classification neural network

The currently widely used lightweight neural networks still have the problems such as large number of calculations and parameters, which make cheap mobile devices with low computation resources cannot quickly complete the image classification tasks. Aiming at this problem, this paper proposed a lightweight neural network that was more suitable for use on cheap mobile devices with low computation resources. This paper introduced cheap linear operations and concatenations of feature maps to reduce the number of calculations and parameters of the neural network. Also, this paper introduced improved residual structure, attention mechanism and label smoothing to improve the accuracy of result. Experiments based on PD-38 dataset show that the proposed neural network can achieve higher classification accuracy by using a smaller number of calculations and parameters than traditional lightweight neural networks. Experiments on the public dataset CIFAR-10 further show that the neural network is universal.