南京师大学报（自然科学版）2025，Vol.48Issue(3)：120-128,9.DOI:10.3969/j.issn.1001-4616.2025.03.014
基于图像融合和注意力机制的图像分类
Image Classification Based on Image Fusion and Attention Mechanism
摘要
Abstract
As a key task in the field of computer vision,image classification is of great significance in many application scenarios.Aiming at the accuracy and robustness of image classification,a classification method based on image fusion and attention mechanism is proposed.Firstly,ResNet-152 is selected as the basic model of image classification,and the public data set is preprocessed.In the feature fusion stage,three parallel branches are used,and convolution kernels with different sizes are used to extract features.Then,the attention mechanism is introduced after the residual network structure,and the Gram matrix,average pooling and maximum pooling are integrated to highlight the areas where the model is beneficial to classification.In the experimental stage,through a large number of experiments on public image data sets,the results show that the proposed method has a good effect in practical application,and the classification accuracy has increased from the initial 96.68%to 98.87%.In addition,compared with traditional methods,it has better robustness.Therefore,this study provides an effective improvement method for the field of image classification,which has a wide application prospect.关键词
图像融合/注意力机制/深度学习/图像分类/卷积网络Key words
image fusion/attention mechanisms/deep learning/image classification/convolutional networks分类
信息技术与安全科学引用本文复制引用
黄文秀,周术诚,陈新元,周忠眉,王榕国..基于图像融合和注意力机制的图像分类[J].南京师大学报（自然科学版）,2025,48(3):120-128,9.基金项目
国家自然科学基金项目(61672159)、福建省自然科学基金项目(2022J01398)、福建省中青年教师科技类教育科研项目(JAT211024)、福建省中青年教师科技类教育科研项目(JAT211001)、福建省终身教育提质培优项目(ZS22026). （61672159）
