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

Image recognition model migration method and device, equipment and storage medium

An image recognition and model technology, applied in the field of artificial intelligence, can solve the problems of poor generalization of image recognition models and inability to design anchor sets, etc., to achieve the effect of improving generalization, improving recognition efficiency, and improving migration efficiency.

Active Publication Date: 2021-05-14
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, related technologies cannot design a reasonable anchor point set for the target domain when the real annotations of the image samples in the target domain cannot be obtained, and the generalization of the image recognition model is not strong.

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
  • Image recognition model migration method and device, equipment and storage medium
  • Image recognition model migration method and device, equipment and storage medium
  • Image recognition model migration method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0035] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the nature of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and de...

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 an image recognition model migration method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring head feature maps of a source domain image sample and a target domain image sample; determining object prediction labels of the two samples based on the head feature maps of the two samples; determining model training loss based on difference information between the feature maps of the two samples and difference information between an object prediction label and a true value label of the source domain image sample; and adjusting parameters of the image recognition model according to the model training loss to obtain a migrated image recognition model. Single-stage domain migration is realized based on the head feature map, and the migration efficiency and generalization of the model can be improved. In addition, the model can be migrated to a real scene for application by utilizing simulation data with true value annotation and real scene data without true value annotation. For example, the method and device can be used for a model domain migration task of an automatic driving scene.

Description

technical field [0001] The embodiments of the present application relate to the technical field of artificial intelligence, and in particular to a migration method, device, equipment, and storage medium of an image recognition model. Background technique [0002] With the development of artificial intelligence technology, there are more and more researches and applications on domain transfer. Domain migration is used to migrate the model from the data distribution of the source domain to the data distribution of the target domain, and the migrated model can be used to perform tasks corresponding to the target domain. [0003] Taking the image recognition model as an example, related technologies realize domain migration through a two-stage image recognition method, that is, designing a set of reasonable anchor point sets (namely, candidate frame sets) for the target domain, and based on the anchor point set for image recognition model The parameters are fine-tuned to obtain...

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): G06K9/62G06N3/08
CPCG06N3/08G06F18/253G06F18/214
Inventor 刘畅
Owner TENCENT TECH (SHENZHEN) CO 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