Unlock instant, AI-driven research and patent intelligence for your innovation.

Mixed pooling method based on maximum pooling and average pooling

A technology of max pooling and hybrid pooling, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as neglect of max pooling methods and weakening of average pooling methods.

Active Publication Date: 2020-03-31
DONGHUA UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the maximum pooling method ignores the performance of some effective features, and the average pooling method weakens the performance of the most distinctive features.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Mixed pooling method based on maximum pooling and average pooling
  • Mixed pooling method based on maximum pooling and average pooling
  • Mixed pooling method based on maximum pooling and average pooling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Below in conjunction with specific embodiment, further illustrate the present invention. It should be understood that these examples are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the teachings of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the appended claims of the present application.

[0030] A kind of hybrid pooling method based on maximum pooling and average pooling provided by the present invention comprises the following steps:

[0031] Step 1. Input the image X into the convolutional layer, and the formula used by the convolutional layer is shown in formula (1):

[0032]

[0033] In formula (1), X*W means that the image X is convolved with the convolution area W; x(i+m, j+n) means that the pixel x(i,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a mixed pooling method based on maximum pooling and average pooling. The hybrid pooling method based on maximum pooling and average pooling is formed by combining the advantages of maximum pooling and average pooling and utilizing the mathematical significance and the practical significance of square average, and the pooling method can better reserve the texture features and the background features of the images, so that the image classification precision is improved, and the classification loss is reduced. The method is an experiment based on DenseNet, but the methodcan be applied to other convolutional neural networks using pooling layers, such as ResNet, FastRCNN and the like.

Description

technical field [0001] The invention relates to a method for improving a neural network pooling layer, relating to the field of artificial intelligence, in particular to a hybrid pooling method based on maximum pooling and average pooling. Background technique [0002] Image classification is an image processing method that distinguishes different types of objects according to the different characteristics reflected in the image information. It uses computers to conduct quantitative analysis on images, and classifies each pixel or region of the image or image into one of several categories to replace human visual interpretation. In recent years, with the breakthrough of deep learning in the field of image processing, image classification using deep learning has become a research hotspot. [0003] Densely Connected Convolutional Networks (DenseNet) is an improved feed-forward neural network based on Convolutional Neural Network (CNN). Its artificial neurons can respond to su...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/24
Inventor 卢婷宋佳霏黄若琳张磊常姗
Owner DONGHUA UNIV