Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Capsule network rapid routing method based on kernel density estimation and mean shift

A technology of kernel density estimation and mean shift, applied in the fields of deep learning and computer vision, it can solve problems such as blocking costs, and achieve the effect of improving time efficiency and recognition performance.

Inactive Publication Date: 2019-09-20
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The dynamic routing mechanism in the capsule network can help the network achieve better results with fewer parameters, but what hinders the widespread application of the capsule network is the cost of dynamic routing calculations

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
  • Capsule network rapid routing method based on kernel density estimation and mean shift
  • Capsule network rapid routing method based on kernel density estimation and mean shift
  • Capsule network rapid routing method based on kernel density estimation and mean shift

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0043] Such as figure 1 As shown, the present invention discloses a capsule network fast routing method based on kernel density estimation and mean shift, which mainly includes the following steps:

[0044] Step 1. According to the kernel density estimation formula, the probability density function for multi-clustering problems is given;

[0045] Step 2, based on the probability density function given in step 1, the dynamic routing process is modeled as an optimization problem;

[0046] Step 3, using the mean shift algorithm to solve the optimization problem in step 2;

[0047] In step 4, the result obtained in step 3 is used as the output of the capsule network to obtain the final classification result.

[0048] Steps 1-4 will be described in ...

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 provides a capsule network rapid routing method based on kernel density estimation and mean shift. The method comprises the steps of giving a probability density function for a multi-clustering problem according to a kernel density estimation formula, modeling the dynamic routing process into an optimization problem, solving the optimization problem by utilizing a mean shift algorithm, and taking a solving result as the output of a capsule network to obtain a final classification result. Compared with the prior art, the dynamic routing time efficiency is greatly improved, at the same time, the identification performance of the capsule network is also improved.

Description

technical field [0001] The invention relates to the technical fields of computer vision and deep learning, in particular to a capsule network fast routing method based on kernel density estimation and mean shift. Background technique [0002] In recent years, convolutional neural networks have made great achievements in the fields of image classification, target detection, and semantic segmentation. Convolutional neural networks are usually composed of convolutional layers, pooling layers, and fully connected layers. The pooling layer is An important part of the convolutional neural network, typically the maximum pooling and average pooling operations, the pooling layer can reduce the size of the feature map, while reducing the number of network parameters, thereby reducing the amount of calculation of the model, but the pooling layer There is also the problem of loss of spatial position information. [0003] Aiming at the problem of the loss of spatial position information...

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): G06K9/62
CPCG06F18/2321
Inventor 张索非谢奔
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com