电子学报2025，Vol.53Issue(8)：2779-2793,15.DOI:10.12263/DZXB.20250028
背景感知机制的图像分类网络
Image Classification Network of Background Perception Mechanism
摘要
Abstract
In view of the lack of effective understanding of complex scenes in image classification methods,which leads to the limited ability of models to capture key features and thus affects the classification accuracy,this paper proposes an image classification network of background perception mechanism(BPMNet).Firstly,the background perception(BP)module is proposed.Through a dual-branch structure,the foreground and background information are processed respective-ly,the contribution degree of the input features is dynamically adjusted,and the context support role of the background in-formation on the foreground features is strengthened to enhance the model's perception ability of background information.Then,combined with the BP module,the background perception attention(BPA)module is designed.While considering the local feature information and long-range dependency relationship,it also pays attention to the relationship between the fore-ground and background of the image,and dynamically regulates the influence degree of the background information on the features of the subject target and enhances the discriminability and positioning ability of key target features.Finally,the background perception module and the background perception attention module are embedded in the residual block to achieve feature transfer from shallow details to deep semantics,and the feature representation ability of foreground targets in complex scenes is enhanced by combining local details and global semantics.Compared with other mainstream networks,the classification accuracy of BPMNet achieved on the image data sets such as CIFAR-10,CIFAR-100,SVHN,Imagenette and Imagewoof,are 96.95%,80.85%,97.68%,90.10%and 81.70%,respectively,which increased by 2.39%,3.17%,2.36%,2.30%and 2.67%on average.Compared with the current advanced network models,the proposed method can enhance the model's understanding of complex scenes,improve the ability to express key regions,extract key features more effectively,and further improve the robustness and generalization ability of the model.关键词
图像分类/背景感知机制/背景感知注意力/局部特征/神经网络Key words
image classification/background perception mechanism/background perception attention/local feature/neural network分类
信息技术与安全科学引用本文复制引用
袁姮,冉超,张晟翀..背景感知机制的图像分类网络[J].电子学报,2025,53(8):2779-2793,15.基金项目
国家自然科学基金(No.61601213) （No.61601213）
国防预研基金(No.172068) （No.172068）
辽宁省教育厅重点基金(No.LJYL049) National Natural Science Foundation of China(No.61601213) （No.LJYL049）
National Defense Preliminary Research Fund(No.172068) （No.172068）
Key Fund of Liaoning Provincial Department of Education(No.LJYL049) （No.LJYL049）
