计算机应用研究2024，Vol.41Issue(7)：2235-2240,6.DOI:10.19734/j.issn.1001-3695.2023.09.0513
融合多粒度注意力特征的小样本分类模型
Few-shot classification model incorporating multi-granular attention features
摘要
Abstract
In the few-shot classification tasks,existing CNN models suffer from insufficient feature extraction,limited feature diversity and weak differentiation between classes in few-shot datasets,leading to low classification accuracy.To address these issues,this paper proposed a few-shot classification model called FMAF.Firstly,this method incorporated multi-granularity thought into the architecture of CNN feature extraction network to enhance feature diversity.Secondly,after the multi-granular feature extraction network,FMAF added a self-attention layer to extract key features from the multi-granular image features,based on the multi-granular attention features,FMAF employed a feature fusion method to combine the information from multiple-granularity attention features,highlighted the crucial features and improved feature representativeness.Finally,this paper uti-lized two classical few-shot datasets for experimental verification on miniImageNet and tieredImageNet.Experimental results show that FMAF method can effectively improve the accuracy and efficiency of classification.关键词
小样本学习/多粒度特征融合/自注意力机制/标签传播Key words
FSL/multi-granular feature fusion/self-attention mechanism/label propagation分类
信息技术与安全科学引用本文复制引用
韩岩奇,苟光磊,李小菲,朱东华..融合多粒度注意力特征的小样本分类模型[J].计算机应用研究,2024,41(7):2235-2240,6.基金项目
国家自然科学基金资助项目(62141201) （62141201）
重庆市教委科学技术研究项目(202201102) （202201102）
