摘要
本文针对小样本图像分类问题,提出一种基于样本对的元学习(Pairwise-based Meta Learning,PML)方法.利用传递迁移学习对预训练好的Resnet50模型进行微调,得到一个更适应小样本任务的特征编码器,将该特征编码器作为元学习模型的初始特征编码器来训练模型,进一步增强了元学习模型的泛化能力;同时,本文还基于支持集与查询集样本之间的相似性提出元损失函数(Meta Loss,ML),其考虑了特征空间中查询集所有样本的相互关系,以此来缩小正样本类内距离,增加正负样本类间距离,从而提高分类精度.实验结果表明,本文的方法在1-shot、5-shot任务上分别达到了77.65%、89.65%的分类精度,较最新的元学习方法Meta-baseline分别提高7.38%、5.65%.
In this paper,a pairwise-based meta learning(PML)method is proposed for few-shot image classification.Transitive transfer learning is used to fine tune the pre-trained Resnet50model to get a feature encoder that is more suitable for few shot task.The feature encoder is used as the initial feature encoder of the meta-learning model to train the model,which further enhances the generalization ability of the meta-learning model.Based on the similarity between the support set and the query set samples,a meta loss(ML)function is proposed,which considers the relationship between all the samples of the query set in the feature space,so as to reduce the within-class distance of positive samples and increase the between-class distance of positive and negative samples,thus improving the classification accuracy.The experimental results show that the classification accuracy of the methods in this paper is77.65%and89.65%on1-shot and5-shot tasks,respectively,and it is7.38%and5.65%higher than the latest meta-learning method,Meta-baseline.
作者
李维刚
甘平
谢璐
李松涛
LI Wei-gang;GAN Ping;XIE Lu;LI Song-tao(Engineering Research Center for Metallurgical Automation and Measurement Technology(Ministry of Education),Wuhan University of Science and Technology,Wuhan,Hubei 430081,China)
出处
《电子学报》
EI
CAS
CSCD
北大核心
2022年第2期295-304,共10页
Acta Electronica Sinica
基金
国家自然科学基金面上项目(No.51774219)
湖北省重点研发计划(No.2020BAB098)。
关键词
小样本图像
传递迁移学习
元学习
元损失函数
few-shot image
transitive transfer learning
meta learning
meta loss function
