自动化与信息工程2025，Vol.46Issue(1)：59-65,7.DOI:10.3969/j.issn.1674-2605.2025.01.009
基于类注意力的原型网络改进方法
Improvement Method of Prototype Network Based on Class Attention
摘要
Abstract
Small sample learning is an important challenge in image classification tasks,which can effectively solve the problem of reduced model accuracy due to limited data volume.A prototype network improvement method based on class attention is proposed to address the problem of difficulty in accurately obtaining common features within classes in small sample learning.Using mask images for data preprocessing and image enhancement to improve the quality of raw data;Introducing attention mechanism to selectively focus on important information in feature maps to enhance feature extraction capability;Design a class attention module to extract class prototypes with attention information.The experimental results show that on the miniImageNet dataset,the classification accuracy of this method has improved by 2%compared to the baseline,verifying its effectiveness.关键词
原型网络/小样本学习/数据增强/类注意力/图像分类Key words
prototype network/small sample learning/data enhancement/class attention/image classification分类
计算机与自动化引用本文复制引用
曹增辉,陈浩,曹雅慧..基于类注意力的原型网络改进方法[J].自动化与信息工程,2025,46(1):59-65,7.基金项目
广东省基础与应用基础研究重大项目(2023B0303000009) （2023B0303000009）
