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

Training method, training equipment, using method and using equipment of multi-task recognition model, and storage medium

A technology of recognition model and training method, applied in the field of image processing, can solve the problem of low recognition efficiency of multi-task recognition model

Active Publication Date: 2021-03-30
UBTECH ROBOTICS CORP LTD
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a training method and using method, equipment and storage medium of a multi-task recognition model, which can solve the problem of low recognition efficiency of the multi-task recognition model in the prior art

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
  • Training method, training equipment, using method and using equipment of multi-task recognition model, and storage medium
  • Training method, training equipment, using method and using equipment of multi-task recognition model, and storage medium
  • Training method, training equipment, using method and using equipment of multi-task recognition model, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0039] see figure 1 , figure 1 It is a flowchart of a training method for a multi-task recognition model in an embodiment of the present invention.

[0040] Step 101. Obtain a sample image. The sample image includes a first sample image, a second sample image, and a third sample image. The first sample image includes several sample images with independent face attributes, and the second sample image includes A sample image of several feature-coupled face attribut...

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 training method, training equipment, a using method and using equipment of a multi-task recognition model, and a storage medium. An initial feature sharingmodel is trained through employing a sample image which comprises a plurality of face attributes with independent features, then a sample image which comprises a plurality of face attributes with coupled features is added for training, finally, a decoupling model part is added to the model, and a sample image containing a human face posture is added for training, so that the training of the multi-target task recognition model can be realized by gradually increasing human face attributes, and the sample image with the human face attributes with independent features can be fully utilized to realize feature sharing; and the decoupling effect on the coupling features is realized by adding the decoupling model, so that the recognition accuracy of the multi-task target recognition model can be effectively ensured, and the recognition efficiency can be ensured while the multi-face attribute recognition precision of the single model is ensured.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a training method and usage method, equipment and storage medium of a multi-task recognition model. Background technique [0002] The more common topic in face attribute detection is age and gender detection and recognition, but the general solution is to solve it by dividing into two models. When we want to complete the 7 tasks of gender, age, smile, face image quality, face value, mask status, and glasses status, we need to use 7 models for detection respectively. However, there will be the following problems: if there are n For a task, the response speed of recognition must be multiplied by n, and the recognition efficiency is low. Contents of the invention [0003] The main purpose of the present invention is to provide a multi-task recognition model training method, using method, device and storage medium, which can solve the problem of low recognition ef...

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): G06K9/00G06K9/62
CPCG06V40/168G06F18/214
Inventor 曾钰胜程骏庞建新
Owner UBTECH ROBOTICS CORP LTD
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