| 注册
首页|期刊导航|电子科技|融合注意力和胶囊池化的轻量型胶囊网络

融合注意力和胶囊池化的轻量型胶囊网络

朱子豪 宋燕

电子科技2024,Vol.37Issue(5):1-8,31,9.
电子科技2024,Vol.37Issue(5):1-8,31,9.DOI:10.16180/j.cnki.issn1007-7820.2024.05.001

融合注意力和胶囊池化的轻量型胶囊网络

Lightweight Capsule Network Fusing Attention and Capsule Pooling

朱子豪 1宋燕1

作者信息

  • 1. 上海理工大学 光电信息与计算机工程学院,上海 200093
  • 折叠

摘要

Abstract

In view of the inefficiency of feature information propagation in capsule networks and the huge com-putational overhead in the routing process,a graph pooling capsule network that combines attention and capsule poo-ling is proposed.The network mainly has the following two advantages:1)The capsule attention is proposed,and the attention is applied to the primary capsule layer,which enhances the attention to the important capsules,and im-proves the accuracy of the prediction of the lower capsules to the higher capsules;2)A new capsule pooling is pro-posed.The capsule with the largest weight is screened out at the corresponding positions of all feature maps in the primary capsule layer,and the effective feature information is represented by a small number of important capsules while reducing the number of model parameters.Results on public data sets show that the proposed capsule network achieves the accuracy of 92.60%on CIFAR10 and has excellent robustness against white-box adversarial attacks on complex datasets.In addition,the proposed capsule network achieves 95.74%accuracy on the AffNIST data set with superior affine transformation robustness.The calculation efficiency results show that the amount of floating-point operations of the proposed capsule is reduced by 31.3%and the number of parameters is reduced by 41.9%when compared with traditional CapsNet.

关键词

深度学习/图像分类/胶囊网络/胶囊池化/注意力机制/鲁棒性/对抗攻击/轻量型

Key words

deep learning/image classification/capsule network/capsule pooling/attention mechanism/ro-bustness/adversarial attack/lightweight

分类

信息技术与安全科学

引用本文复制引用

朱子豪,宋燕..融合注意力和胶囊池化的轻量型胶囊网络[J].电子科技,2024,37(5):1-8,31,9.

基金项目

国家自然科学基金(62073223) (62073223)

上海市自然科学基金(22ZR1443400) (22ZR1443400)

航天飞行动力学技术国防科技重点实验室开放课题(6142210200304) National Natural Science Foundation of China(62073223) (6142210200304)

Shang-hai Natural Science Foundation(22ZR1443400) (22ZR1443400)

Open Project of the National Defense Science and Technology Key Laboratory of Aer-ospace Flight Dynamics(6142210200304) (6142210200304)

电子科技

1007-7820

访问量0
|
下载量0
段落导航相关论文