首页|基于原型嵌入图网络的小样本图像分类

基于原型嵌入图网络的小样本图像分类

扫码查看
原文链接
  • 万方数据
  • 维普
针对在小样本图像分类中传统骨干卷积网络进行特征提取时会有上下文信息单一和感受野受限以及边特征相似度度量缺乏全局性问题,本文提出了一种基于原型嵌入图网络的小样本图像分类算法.首先,将CBAM产生的权重值与ASPP以不同采样率获取的不同尺度特征进行相乘的特征作为图网络的节点嵌入特征.然后,采用原型网络的方法在度量模块中构建了原型节点,使得成对节点之间的相似性计算转化为单个节点与原型节点相似性的和计算,将得到的相似度作为边特征输入图神经网络.最后,利用双图结构在多个更新代后将标签信息从有标签样本传播到无标签样本.在以ResNet-12为骨干卷积网络的算法分类任务中,本文在miniImageNet、tieredImageNet、CUB-200-2011和CIFAR-FS 4个数据集上的5-way 1-shot的任务分类准确率分别达到了71.47％、75.41％、86.21％和79.84％,在以Conv-4作为骨干卷积网络中,本文提出的算法在5-way 1-shot和5-way 5-shot任务中都优于现有的图网络方法.
Few-shot image classification based on prototype embedding graph network
Traditional backbone convolutional networks for feature extraction in few-shot image classification suffer from the problems of single context information,limited receptive field,and lack of global edge feature similarity measurement. In this paper,we propose a few-shot image classification algorithm based on prototype embedding graph network. First,the feature obtained by multiplying the weight values generated by CBAM with the features of different scales obtained by ASPP at different sampling rates is used as the node embedding feature of the graph network. Then,the prototype nodes are constructed in the measurement module using the prototype network method,transforming the similarity calculation between paired nodes into the sum of the similarity between a single node and the prototype node,and using the obtained similarity as the edge feature input to the graph neural network. Finally,the label information is propagated from labeled samples to unlabeled samples through the dual graph structure after multiple update iterations. In the classification task using ResNet-12 as the backbone convolutional network,our algorithm achieves classification accuracies of 71.47％,75.41％,86.21％,and 79.84％ on the miniImageNet,tieredImageNet,CUB-200-2011,and CIFAR-FS datasets,respectively,for the 5way-1shot task. In the backbone convolutional network using Conv-4,our proposed algorithm outperforms existing graph network methods in both 5way-1shot and 5way-5shot tasks.

graph neural networkfew-shot learningprototype nodesmulti-scale feature fusionimage classification

陈望、李志玲、王前、包春梅、王林

展开 >

贵州民族大学数据科学与信息工程学院 贵阳 550025

贵州省模式识别与智能系统重点实验室贵州民族大学 贵阳 550025

图神经网络 小样本学习 原型节点 多尺度特征融合 图像分类

国家自然科学基金贵州省科技计划项目贵州省科技计划项目贵州省科技计划项目贵州省科技计划项目贵州省青年科技人才成长项目贵州省教育厅自然科学研究项目贵州省教育厅自然科学研究项目贵州省教育厅自然科学研究项目贵州省教育厅青年科技人才成长项目贵州省教育厅青年科技人才成长项目贵州省深化新时代教育评价改革试点贵州省模式识别与智能系统重点实验室开放课题

62241206黔科合基础-ZK[2022]一般195黔科合基础-ZK[2023]一般143黔科合基础-ZK[2022]一般550黔科合平台人才-ZCKJ[2021]007黔教合KY字[2021]104黔教技[2023]012号黔教技[2022]015号黔教技[2023]061号黔教合KY字[2021]115黔教合KY字[2021]110GZMUKL[2022]KF01

2024

10.19651/j.cnki.emt.2315182

电子测量技术
北京无线电技术研究所

电子测量技术

CSTPCD北大核心
影响因子：1.166
ISSN：1002-7300
年,卷(期)：2024.47(5)
  • 4