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

Cross-domain model training method, device and equipment

A model training and cross-domain technology, applied in the Internet field, can solve problems such as weak cross-domain robustness, and achieve the effect of improving cross-domain robustness

Pending Publication Date: 2022-07-29
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

That is, the trained model cannot classify cross-domain attacks very well, and the cross-domain robustness 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
  • Cross-domain model training method, device and equipment
  • Cross-domain model training method, device and equipment
  • Cross-domain model training method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The embodiments of this specification provide a cross-domain model training method, apparatus, device, and storage medium.

[0021] In order to make those skilled in the art better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described The embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments of the present specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0022] In the first aspect, as figure 1 shown, figure 1 A schematic flowchart of a cross-domain model training method provided in the embodiment of this specification may include the follow...

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 cross-domain model training method, device and equipment. A training sample comprising N domains is obtained, the training sample comprises domain labels, and N is a natural number larger than 1; sample features of the training sample are extracted, a prediction sample is generated according to the sample features, and domain labels of the prediction sample and the training sample are the same; the prediction samples are classified according to the domain labels, multiple branches are generated, and the multiple branches comprise a main branch not containing the domain labels and at least one sub-branch containing the domain labels; respectively determining loss values of the plurality of branches, and fusing the plurality of loss values to determine a target loss value; and training and generating a target model according to the target loss. By combining training samples from different domains to perform adversarial classification of multiple branches, model training without unknown scene data is realized, and a target model adaptive to multiple scenes is generated.

Description

technical field [0001] This specification relates to the field of Internet technologies, and in particular, to a cross-domain model training method, device, and device. Background technique [0002] In the field of risk control, the trained risk control model will encounter a variety of scenarios with very different representations during deployment. This will encounter a relatively mature model in a scenario, and there will be inconsistencies when deploying an unknown new scenario. fit situation. That is, the trained model cannot classify cross-domain attacks well, and the cross-domain robustness is not strong. [0003] Based on this, a more stable cross-domain model training scheme is required. SUMMARY OF THE INVENTION [0004] The embodiments of this specification provide a cross-domain model training method, apparatus, device, and storage medium, to solve the following technical problem: a more stable cross-domain model training solution is required. [0005] To sol...

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): G06V10/776G06V10/774G06V10/764G06V40/16G06K9/62
CPCG06F18/217G06F18/241G06F18/214
Inventor 武文琦
Owner ALIPAY (HANGZHOU) INFORMATION TECH 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

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