基于改进DPGN的少样本图像分类算法研究  

Research on image classification algorithm with few-shot based on im proved DPGN

作　　者：王玲 孙莹 王鹏[1] 白燕娥[1] WANG Ling;SUN Ying;WANG Peng;BAI Yan'e(Changchun University of Science and Technology,Changchun 130022,China)

机构地区：[1]长春理工大学计算机科学技术学院,长春130022

出　　处：《重庆理工大学学报（自然科学）》2024年第2期161-169,共9页Journal of Chongqing University of Technology：Natural Science

基　　金：吉林省自然科学基金项目(20210101413JC)。

摘　　要：DPGN(distribution propagation graph network)是基于深度学习的少样本图像分类算法,在数据稀疏的条件下可以顺利完成图像分类,但其分类的准确率仍需进一步提升。以DPGN算法为研究对象,提出SFOD_DPGN(SinAM_FRN_layer_ODConv_DM&EMD_distribution propagation graph network)算法。在骨干神经网络Resnet12的残差块中融入注意力机制;将Resnet12网络中批量归一化与ReLu激活函数搭配使用的方式改为滤波器响应归一化与阈值线性单元激活函数搭配使用的方式;在分类器模块中选用全维动态卷积替换普通卷积;使用马氏距离和推土机距离替换L2距离度量函数。在CUB-200-2011数据集上的实验表明,在5way-1shot和5way-5shot分类任务下,SFOD_DPGN算法比DPGN算法的准确率提升约7.97%和2.66%。The distribution propagation graph network(DPGN)is a few-shot image classification algorithm based on deep learning.Unfortunately,the DPGN algorithm completely ignores semantic information,which is important for fine-grained classification.Therefore,it delivers poor classification performances.This paper proposes a new Few-shot learning algorithm based on the DPGN algorithm,SinAM-FRN_layer-ODConv-DM&EMD_Distribution Propagation Graph Network(SFOD_DPGN).First,to address the inability to extract image features by the feature extraction module of the DPGN algorithm,the SimAM attention mechanism is integrated into four residual blocks of the feature extraction network ResNet12.The SimAM attention mechanism can generate three-dimensional weights for feature maps from both spatial and channel dimensions,and then aggregates the generated weights with the feature maps to enable the improved ResNet12 to learn more and richer image features;Second,in view that the normalization method of the ResNet12 is affected by the number of images selected in training,the combination of batch normalization and the ReLu activation function in the main path of each residual block of the ResNet12 is changed to the combination of the filter response normalization(FRN)and the threshold linear unit activation function(TLU).Because of the FRN without mean operation,it easily leads to activation with arbitrary bias far from zero.If the FRN combines with the ReLu activation function,this bias has adverse effects on training.This paper employs the TLU after the FRN to address the problem.The SFOD_DPGN algorithm improves the classification accuracy and ensures its inference speed.Then,it optimizes the classifier module of the DPGN algorithm.To solve poor classification performance of the classifier module,the full dimensional dynamic convolution(ODConv)is selected to replace the common convolution in the classifier module.The ODconv employs a linear combination of n convolutional kernels and parallel strategies to introduce multidimensional atte

关 键 词：深度学习 少样本图像分类 注意力机制 全维动态卷积 马氏距离 推土机距离 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]