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

Dilated-convolution method based on deep convolutional adversarial network model

A network model and deep convolution technology, applied in the field of deep learning neural network, can solve the problems of small feature range and low learning efficiency, and achieve the effect of stable network training

Inactive Publication Date: 2018-04-03
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this case, the range of features learned by the generator is small and the learning efficiency is low

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
  • Dilated-convolution method based on deep convolutional adversarial network model
  • Dilated-convolution method based on deep convolutional adversarial network model
  • Dilated-convolution method based on deep convolutional adversarial network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0027] This embodiment discloses an atrous convolution method based on a deep convolutional confrontation network model, which specifically includes the following steps:

[0028] Step S1. Construct the original generative adversarial network model, and input the image generated by the generator to the discriminator for network training.

[0029] Step S2, constructing a deep convolutional neural network as a generator and a discriminator;

[0030] Different convolution kernels are reflected in different matrix values ​​and different numbers of rows and columns.

[0031] Construct multiple convolution kernels. In the process of processing images, different convolution kernels mean that different features of generated images can be learned during network training.

[0032] In the traditional confrontational network model, the convolution kernels used by the discriminator and the generator are fixed in size and have the same value. In this case, the training efficiency is relativ...

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 discloses a dilated-convolution method based on a deep convolutional adversarial network model, and belongs to the fields of deep learning and neural networks. The dilated-convolution method includes the following steps: S1, constructing an original generative adversarial network (GAN) model; S2, constructing deep convolutional neural networks to use the same as a generator and a discriminator; S3, initializing random noises, and inputting the same into the generator; S4, utilizing dilated convolution to carry out convolution operations on images in the neural network; and S5, inputting a loss function value, which is obtained by the dilated-convolution operations, into the generator for subsequent training. According to the dilated-convolution method based on the deep convolutional adversarial network model constructed in the invention, a convolution manner of the discriminator and the generator after receiving a picture is changed, the discriminator and the generator are enabled to learn features of the image in a larger range, and thus robustness of the entire network training model can be improved.

Description

technical field [0001] The invention relates to the technical field of deep learning neural networks, in particular to an atrous convolution method based on a deep convolutional confrontation network model. Background technique [0002] Generative Adversarial Network (GAN for short) is a deep learning framework proposed by Goodfellow in 2014. It is based on the idea of ​​"game theory" and constructs two models, the generator and the discriminator. The former The image is generated by inputting (0, 1) uniform noise or Gaussian random noise, which discriminates the input image to determine whether it is an image from the dataset or an image produced by the generator. [0003] In the traditional confrontational network model, the discriminator often operates through the original convolution kernel, analyzes the features of the image generated by the generator, and learns a new feature. It often needs to learn an old feature. Only after it is over. In this case, the range of f...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2413
Inventor 周智恒李立军
Owner SOUTH CHINA UNIV OF TECH
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