Parameterized Pooling Convolution Neural Network for Image Classification

JIANG Ze-tao; QIN Jia-qi; ZHANG Shao-qin

doi:10.3969/j.issn.0372-2112.2020.09.009

您当前的位置：

首页 >

文章列表页 >

Parameterized Pooling Convolution Neural Network for Image Classification

更新时间：2025-12-08

- Parameterized Pooling Convolution Neural Network for Image Classification
- Acta Electronica Sinica Vol. 48, Issue 9, Pages: 1729-1734(2020)
- 作者机构：
  
  1. 桂林电子科技大学广西图像图形与智能处理重点实验室,广西,桂林,541004
  2. 桂林电子科技大学信息科技学院,广西,桂林,541004
  3. 南昌航空大学,江西,南昌,330063
  4. 桂林电子科技大学广西图像图形与智能处理重点实验室,广西,桂林,541004
  5. 桂林电子科技大学信息科技学院,广西,桂林,541004
  6. 南昌航空大学,江西,南昌,330063
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61876049, No.61762066);Science and Technology Project of Guangxi Zhuang Autonomous Region (No.AC16380108);Guangxi Key Laboratory of Image and Graphic and Intelligent Processing (No.GIIP201701, No.GIIP201801, No.GIIP201802, No.GIIP201803);Postgraduate Education Innovation Plan of Guangxi Province (No.YCBZ2018052, No.2019YCXS043)
- DOI：10.3969/j.issn.0372-2112.2020.09.009
  CLC： TP391
- Published Online：25 September 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
JIANG Ze-tao, QIN Jia-qi, ZHANG Shao-qin. Parameterized Pooling Convolution Neural Network for Image Classification[J]. Acta Electronica Sinica, 2020, 48(9): 1729-1734.
DOI：

JIANG Ze-tao, QIN Jia-qi, ZHANG Shao-qin. Parameterized Pooling Convolution Neural Network for Image Classification[J]. Acta Electronica Sinica, 2020, 48(9): 1729-1734. DOI： 10.3969/j.issn.0372-2112.2020.09.009.

摘要

传统的卷积神经网络使用池化层对信息进行降维操作，通常会造成信息损失，从而影响网络的表达能力.针对这一问题，使用参数池化层（Parameterized Pooling Layer）替代传统卷积神经网络中的池化层，提出参数池化卷积神经网络（Parameterized Pooling CNN，PPCNN）.参数池化层在仅仅增加了少量网络参数的情况下，最大可能的保留了卷积神经网络中希望被保留下来的特征；同时，由于增加了池化层前向传播的信息，从而影响了反向传播算法中权值的更新，网络收敛速度更快；实验结果表明，PPCNN模型与传统卷积神经网络模型以及部分改进模型相比，参数池化卷积神经网络模型是有效的.

Abstract

Traditional convolutional neural network uses pooling layer to reduce the dimension of feature

which usually results in information loss

thus affecting the expression ability of the network. To solve this problem

the parameterized pooling layer is used to replace the pooling layer in the conventional convolutional neural network

and the parameterized pooling CNN (PPCNN) is proposed. In the case that only a few network parameters are added in the parameter pooling layer

it is possible to retain the desired features. At the same time

the forward propagation information of the pooling layer is added

which affects the update of weight in the backpropagation algorithm

and the network convergence speed is faster. Compared with the conventional convolutional neural network model and some improved models

experimental results show that the PPCNN model is effective.

关键词

Keywords

references

Views

116

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Lightweight Image Classification Algorithm Based on Multi-Branch Bottleneck Structure

Research of Lightweight Convolution Neural Network Based on Feature Expansion Convolution

Image Classification of Landing Landform Based on Wavelet Transform and Deep Network

Related Author

SU Tian-tian

WANG Hui-min

ZHANG Xiao-feng

XU Xin-zheng

LI Shan

LIU Fang

HAN Xiao

ZHANG Xiao-feng

Related Institution

School of Physics and Information Technology， Shaanxi Normal University

School of Computer Science and Technology, China University of Mining and Technology

Engineering Research Center of Mining Digital Ministry of Education

Faculty of Information Technology， Beijing University of Technology

School of Computer Science and Technology， China University of Mining and Technology

⁰