空间位置矫正的稀疏特征图像分类网络  

Sparse feature image classification network with spatial position correction

作　　者：姜文涛[1] 陈晨 张晟翀[2] Jiang Wentao;Chen Chen;Zhang Shengchong(College of Software,Liaoning Technical University,Huludao,Liaoning 125105,China;Key Laboratory of Optoelectronic Information Control and Security Technology,Tianjin 300308,China)

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125105 [2]光电信息控制和安全技术重点实验室,天津300308

出　　处：《光电工程》2024年第5期66-82,共17页Opto-Electronic Engineering

基　　金：国家自然科学基金资助项目(61172144);辽宁省自然科学基金资助项目(20170540426);辽宁省教育厅重点基金资助项目(LJYL049)。

摘　　要：为稀疏语义并加强对重点特征的关注,增强空间位置和局部特征的关联性,对特征空间位置进行约束,本文提出空间位置矫正的稀疏特征图像分类网络(SSCNet)。该网络以ResNet-34残差网络为基础,首先,提出稀疏语义强化特征模块(SSEF),SSEF模块将深度可分离卷积(DSC)和SE相融合,在稀疏语义的同时增强特征提取能力,并能够保持空间信息的完整性;然后,提出空间位置矫正对称注意力机制(SPCS),SPCS将对称全局坐标注意力机制加到网络特定位置中,能够加强特征之间的空间关系,对特征的空间位置进行约束和矫正,从而增强网路对全局细节特征的感知能力;最后,提出平均池化残差模块(APM),并将APM应用到网络的每个残差分支中,使网络能够更有效地捕捉全局特征信息,增强特征的平移不变性,延缓网络过拟合,提高网络的泛化能力。在多个数据集中,SSCNet相比于其它高性能网络在分类准确率上均有不同程度的提升,证明了其在兼顾全局信息的同时,能够更好地提取局部细节信息,具有较高的分类准确率和较强的泛化性能。To sparse semantics and enhance attention to key features,enhance the correlation between spatial and local features,and constrain the spatial position of features,this paper proposes a sparse feature image classification network with spatial position correction(SSCNet)for spatial position correction.This network is based on the ResNet-34 residual network.Firstly,a sparse semantic enhanced feature(SSEF)module is proposed,which combines depthwise separable convolution(DSC)and SE to enhance feature extraction ability while maintaining the integrity of spatial information;Then,the spatial position correction symmetric attention mechanism(SPCS)is proposed.SPCS adds the symmetric global coordinate attention mechanism to specific positions in the network,which can strengthen the spatial relationships between features,constrain and correct the spatial positions of features,and enhance the network's perception of global detailed features;Finally,the average pooling module(APM)is proposed and applied to each residual branch of the network,enabling the network to more effectively capture global feature information,enhance feature translation invariance,delay network overfitting,and improve network generalization ability.In the CIFAR-10,CIFAR-100,SVHN,Imagenette,and Imagewood datasets,SSCNet has shown varying degrees of improvement in classification accuracy compared to other high-performance networks,proving that SSCNet can better extract local detail information while balancing global information,with high classification accuracy and strong generalization performance.

关 键 词：图像分类 特征提取 空间位置矫正 稀疏语义 对称注意力 全局感知 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]