Few-shot image recognition based on multi-scale features prototypical network  

作　　者：LIU Jiatong DUAN Yong 刘珈彤;DUAN Yong(School of Information Science Engineering,Shenyang University of Technology,Shenyang 110870,P.R.China;Shenyang Key Laboratory of Advanced Computing and Application Innovation,Shenyang 110870,P.R.China)

机构地区：[1]School of Information Science Engineering,Shenyang University of Technology,Shenyang 110870,P.R.China [2]Shenyang Key Laboratory of Advanced Computing and Application Innovation,Shenyang 110870,P.R.China

出　　处：《High Technology Letters》2024年第3期280-289,共10页高技术通讯（英文版）

基　　金：the Scientific Research Foundation of Liaoning Provincial Department of Education(No.LJKZ0139);the Program for Liaoning Excellent Talents in University(No.LR15045).

摘　　要：In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.

关 键 词：few-shot learning multi-scale feature prototypical network channel attention label-smoothing 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]