基于原型增强的元学习分类模型  

Meta-Learning Classification Model Based on Prototype Enhanced

作　　者：翟文茜 李凡长[1] ZHAI Wenxi;LI Fanzhang(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China)

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006

出　　处：《计算机工程与应用》2025年第6期273-281,共9页Computer Engineering and Applications

基　　金：国家重点研发计划(2018YFA0701700,2018YFA0701);国家自然科学基金(67172364,62171672,61902269)。

摘　　要：元学习旨在利用已有的知识经验快速获取新知识、适应新任务,是解决小样本分类问题常用的方法之一。现有的元学习方法在特征提取时通常会忽略任务中支持集样本和查询集样本之间的关系,从而无法获得最具鉴别性的特征,导致类原型不可靠。因此,提出一种基于原型增强的元学习分类模型。该模型主要由两部分组成:特征表示模块与原型修正模块。针对现有方法特征利用不足的问题,特征表示模块利用注意力机制捕捉支持集和查询集样本间的交互信息并更新其特征表示;而针对数据稀缺问题,原型修正模块利用部分查询集的无标签样本扩充支持集,进而对原型位置进行迭代修正。在mini-ImageNet和tiered-ImageNet数据集上的实验结果表明,该模型的分类准确率与其他元学习方法相比有较为显著的提升。Meta-learning aims to utilize existing knowledge and experience to quickly acquire new knowledge and adapt to new tasks.It is one of the commonly used methods to solve few-shot classification problems.Existing meta-learning methods usually ignore the relationship between support set and query set in feature extraction,thus failing to obtain the most discriminative features and leading to unreliable class prototypes.Therefore,this paper proposes a prototype enhanced meta-learning classification model.The model consists of two main components:a feature representation module and a prototype modification module.To address the problem of underutilization of features in existing methods,the feature representation module utilizes attention mechanism to capture the relationship between support set and query set,and update their feature representations.While to address the problem of data scarcity,the prototype modification module utilizes unlabeled samples from query set to expand the support set,and then iteratively corrects the positions of prototypes.Experimental results on mini-ImageNet and tiered-ImageNet datasets show that the classification accuracy of proposed model has significantly improved compared with other meta-learning methods.

关 键 词：原型增强 元学习 小样本学习 图像分类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]