Check patentability & draft patents in minutes with Patsnap Eureka AI!

Data enhancement method and device

A data and parameter technology, applied in the field of data enhancement, can solve the problem of high fitting degree of neural network model, achieve the effect of reducing excessive fitting and improving generalization ability

Pending Publication Date: 2021-11-02
SHENZHEN JIESHUN SCI & TECH IND
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the data enhancement method adopted in the prior art only performs a simple geometric transformation on the picture, and does not change the characteristics of the picture. Using these pictures as the training set to train the neural network model may easily lead to the overfitting of the trained neural network model. high

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
  • Data enhancement method and device
  • Data enhancement method and device
  • Data enhancement method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The embodiment of the present application provides a data enhancement method and device, which are used to generate enhanced data with changed characteristics, so as to reduce the overfitting of the neural network model through the enhanced data.

[0064] The technical solution in this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0065] The method of the present application may be applied to a server, a terminal or other devices with logic processing capabilities, which is not limited in the present application. For the convenience of description, the execution su...

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 embodiment of the invention discloses a data enhancement method and device which are used for generating enhancement data with changed features so as to reduce the situation that the fitting degree of a neural network model is too high through the enhancement data. The embodiment comprises the steps of training an initial generation model, wherein a target generation model is obtained, the target generation model is a neural network model based on a generative adversarial network (GAN), and the target generation model is used for generating a corresponding enhanced picture according to semantic information of an input picture; obtaining a to-be-enhanced picture; determining target semantic information according to the to-be-enhanced picture; and according to the target semantic information, generating a target enhanced picture corresponding to the to-be-enhanced picture through the target generation model.

Description

technical field [0001] The embodiments of the present application relate to the technical field of data enhancement, and in particular, to a data enhancement method and device. Background technique [0002] In the deep learning of image processing, the training neural network model requires a huge amount of data. Therefore, for data sets with a relatively small amount of data, data enhancement is required to increase the data set to meet the requirements of training the neural network model. [0003] In the prior art, the commonly used data enhancement method is to perform operations of rotating, flipping, cropping and scaling the pictures in the data set. However, the data enhancement method adopted in the prior art only performs a simple geometric transformation on the picture, and does not change the characteristics of the picture. Using these pictures as the training set to train the neural network model may easily lead to the overfitting of the trained neural network mo...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/214G06F18/241
Inventor 唐健石伟
Owner SHENZHEN JIESHUN SCI & TECH IND
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com