FuseNet:应用于移动端的轻量型图像识别网络  

FuseNet:lightweight image recognition network for mobile applications

作　　者：田鑫驰 王亚刚[1] 尹钟[1] Tian Xinchi;Wang Yagang;Yin Zhong(School of Optical-Electrical&Computer Engineering,Shanghai University of Science&Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《计算机应用研究》2023年第1期288-293,298,共7页Application Research of Computers

基　　金：国家自然科学基金资助项目(61074087,61703277)。

摘　　要：为解决目前Transformer模型因其巨大的参数量和计算复杂度而无法应用在计算资源相对有限的移动设备中的问题,提出了一种适用于移动端的友好型轻量图像识别网络称为FuseNet。FuseNet利用卷积神经网络提取局部特征信息和自注意力机制擅长对全局信息进行建模的特性,将局部表示与全局表示两者的特性整合至一个特征提取模块,高效融合了两种不同结构的优点达到以较小的模型规模实现较高准确率的目的。实验证明不同参数规模的FuseNet可以在不进行预训练的情况下实现良好的性能,可以很好地应用在移动设备中。FuseNet-B在ImageNet-1K数据集上以14.8 M的参数量实现了80.5%的准确率,性能表现超过了同体量的Transformer模型和卷积神经网络。In order to solve the problem that the Transformer model cannot apply to mobile devices with limited computational resources due to its huge number of parameters and computational complexity,this paper proposed a mobile-friendly lightweight image recognition network called FuseNet.FuseNet utilized convolutional neural network to extract local feature information and self-attention to excel in modeling global information,and it integrated the features of both local and global representations into a single feature extraction module,which efficiently combined the advantages of the two different structures to achieve a high accuracy with a small model size.Experiments demonstrate that FuseNet with different model sizes can achieve good performance without using pre-training and it can well apply to mobile devices.FuseNet-B achieves 80.5%accuracy with 14.8 M parameters on ImageNet-1 K dataset,the performance exceeds the same volume of Transformer models and convolutional neural networks.

关 键 词：卷积神经网络 图像识别 移动设备 轻量型 TRANSFORMER FuseNet 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]