当前位置>主页 > 期刊在线 > 计算机技术 >

计算机技术22年12期

基于改进 ResNet 模型的图像分类方法
蒋博文
(安徽理工大学 计算机科学与工程学院,安徽 淮南 232001)

摘  要:卷积神经网络是一种具有卷积结构的深层前馈神经网络模型,被广泛地应用于图像分类等重要领域。针对原始 ResNet 网络提取特征能力不足的问题,提出一种基于改进 ResNet 模型的图像分类方法。将现有的 SE 通道注意力机制,嵌入到原始 ResNet 网络中每个残差结构的末端,进行跨信道的信息交互,捕捉更显著的通道或像素信息。在 CIFAR-100 和CIFAR-10 数据集上进行大量的实验表明,相对于原始的 ResNet 网络,Top-1 Error 和 Top-5 Error 下降明显。


关键词:卷积神经网络;图像分类;SENet;ResNet



DOI:10.19850/j.cnki.2096-4706.2022.012.021


中图分类号:TP391.4                                        文献标识码:A                                  文章编号:2096-4706(2022)12-0083-03


Image Classification Method Based on Improved ResNet Model

JIANG Bowen

(School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China)

Abstract: The convolutional neural network is a deep feed-forward neural network model with convolutional structure, which is widely used in important fields such as image classification. In view of the problem of insufficient feature extraction capability of the original ResNet network, an image classification method based on improved ResNet model is proposed. The existing SE channel attention mechanism is embedded at the end of each residual structure in the original ResNet network to perform cross-channel information interaction and capture more significant channel or pixel information. Extensive experiments performed on the CIFAR-100 and CIFAR-10 datasets show that the Top-1 Error and Top-5 Error decrease significantly relative to the original ResNet network.

Keywords: convolutional neural network; image classification; SENet; ResNe 


参考文献:

[1] 赵磊,张文,孙振国,等 . 基于色彩分割及信息熵加权特征匹配的刹车片图像分类算法 [J]. 清华大学学报(自然科学版),2018,58(6):547-552.

[2] 黄鹏艳,范永良 . 一种结合纹理特征的极化 SAR 图像分类方法 [J]. 山西建筑,2019,45(14):155-157.

[3] 刘丽,赵凌君,郭承玉,等 . 图像纹理分类方法研究进展和展望 [J]. 自动化学报,2018,44(4):584-607.

[4] WANG Q L,WU B G,ZHU P F,et al. ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks [C]//2020IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle:IEEE,2020:11531-11539.

[5] HU J,SHEN L,ALBANIE S,et al. Squeeze-and-Excitation Networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023.

[6] WOO S,PARK J,LEE J Y,et al. CBAM:Convolutional Block Attention Module [J/OL].arXiv:1807.06521 [cs.CV].[2022-03-22].https://arxiv.org/abs/1807.06521.


作者简介:蒋博文(1997—),男,汉族,安徽合肥人,硕士研究生在读,研究方向:图像分类。