计算机应用 ›› 2021, Vol. 41 ›› Issue (7): 1885-1890.DOI: 10.11772/j.issn.1001-9081.2020091482

所属专题: 人工智能

• 人工智能 • 上一篇    下一篇

基于模糊推理的模糊原型网络

杜炎, 吕良福, 焦一辰   

  1. 天津大学 数学学院, 天津 300350
  • 收稿日期:2020-09-23 修回日期:2020-12-14 出版日期:2021-07-10 发布日期:2020-12-31
  • 通讯作者: 吕良福
  • 作者简介:杜炎(1995-),男,河南信阳人,硕士研究生,主要研究方向:深度学习、小样本学习;吕良福(1979-),男,山东潍坊人,副教授,博士,主要研究方向:人工智能中的深度学习和机器学习;焦一辰(1996-),男,天津人,主要研究方向:深度学习。

Fuzzy prototype network based on fuzzy reasoning

DU Yan, LYU Liangfu, JIAO Yichen   

  1. School of Mathematics, Tianjin University, Tianjin 300350, China
  • Received:2020-09-23 Revised:2020-12-14 Online:2021-07-10 Published:2020-12-31

摘要: 针对真实数据具有的模糊性和不确定性会严重影响小样本学习分类结果这一问题,改进并优化了传统的小样本学习原型网络,提出了基于模糊推理的模糊原型网络(FPN)。首先,从卷积神经网络(CNN)和模糊神经网络两个方向分别获取图像特征信息;然后,对获得的两部分信息进行线性知识融合,得到最终的图像特征;最后,度量各个类别原型到查询集的欧氏距离,得到最终的分类效果。在小样本学习分类的主流数据集Omniglot和miniImageNet上进行一系列实验。实验结果显示:在miniImageNet数据集上,所提模型在5类1样本的实验设置下精度达到49.38%,在5类5样本的实验设置下精度达到67.84%,在30类1样本的实验设置下精度达到51.40%;在Omniglot数据集上该模型的精度相较于传统的原型网络同样有较大提升。

关键词: 小样本学习, 模糊推理, 原型网络, 特征融合, 深度学习

Abstract: In order to solve the problem that the fuzziness and uncertainty of real data may seriously affect the classification results of few-shot learning, a Fuzzy Prototype Network (FPN) based on fuzzy reasoning was proposed by improving and optimizing the traditional few-shot learning prototype network. Firstly, the image feature information was obtained from Convolutional Neural Network (CNN) and fuzzy neural network, respectively. Then, linear knowledge fusion was performed on the two obtained parts of information to obtain the final image features. Finally, to achieve the final classification effect, the Euclidean distance between each category prototype and the query set was measured. A series of experiments were carried out on the mainstream datasets Omniglot and miniImageNet for few-shot learning classification. On miniImageNet dataset, the model achieves accuracy of 49.38% under the experimental setting of 5-way 1-shot, accuracy of 67.84% under the experimental setting of 5-way 5-shot, and accuracy of 51.40% under the experimental setting of 30-way 1-shot; and compared with the traditional prototype network, the model also has the accuracy greatly improved on Omniglot dataset.

Key words: few-shot learning, fuzzy reasoning, prototype network, feature fusion, deep learning

中图分类号: