山西大学学报（自然科学版）2024，Vol.47Issue(4)：761-766,6.DOI:10.13451/j.sxu.ns.2023069
基于D-ResNeXt骨干网络的小样本图像分类算法
Few-shot Image Classification Algorithm Base on D-ResNeXt Backbone Network
摘要
Abstract
Few-shot image classification is currently one of the most important directions in the field of artificial intelligence.In this area,the method based on metric learning is concise and efficient.To address the problem of the backbone network used in the fea-ture extraction stage of current image classification,most existing works use traditional residual networks,which extracts poorly the features of images with large intra-class differences as the method is influenced by the dataset.ResNeXt is an upgraded version of the traditional residual network ResNet,optimizing the problem of low accuracy and large errors in the feature extraction stage of the traditional network.According to its network characteristics,this paper designs a network variant suitable for small sample mod-els,which uses its variant as a backbone network to improve its feature extraction ability,and combines two attention modules to fur-ther improve the recognition effect of intra-class similarity and inter-class variability of images,reduce the influence of irrelevant factors,and effectively improve the overall classification accuracy.关键词
小样本学习/图像分类/注意力机制/度量学习/残差网络Key words
few-shot learning/image classification/attention mechanism/metric learning/residual network分类
信息技术与安全科学引用本文复制引用
杨红菊,翟艳峰..基于D-ResNeXt骨干网络的小样本图像分类算法[J].山西大学学报（自然科学版）,2024,47(4):761-766,6.基金项目
国家自然科学基金(61976128) （61976128）
山西省回国留学人员科研资助项目(2022-008) （2022-008）
