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

Depth measurement model optimization method and device thereof, and storage medium

An optimization method and model technology, applied in the field of deep learning, can solve the problems that it is difficult to improve the discrimination ability of the depth measurement model, and achieve the effect of improving the recognition ability

Pending Publication Date: 2021-10-19
ALIBABA GRP HLDG LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing metric learning methods are not easy to improve the discriminative ability of deep metric models for features

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
  • Depth measurement model optimization method and device thereof, and storage medium
  • Depth measurement model optimization method and device thereof, and storage medium
  • Depth measurement model optimization method and device thereof, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. 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.

[0023] Deep metric learning is mainly used for autonomous learning based on the characteristics of the data to calculate the distance of the data based on the training data, so that the data with similar characteristics are as close as possible, and the data with different characteristics are as far away as possible. Deep metric learning is mostly use...

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 provides a depth measurement model optimization method and device and a storage medium. When the depth measurement model is trained, the graph models output by the depth measurement model for different sample data sets are obtained, the graph consistency loss can be obtained based on the features shown by the different graph models in the structural aspect, and the graph consistency loss can effectively represent the stability of the depth measurement model in the feature identification aspect. The depth measurement model is trained based on the graph consistency loss, the identification capability of the depth measurement model for different features and the same features can be improved in a targeted manner, and the performance of the depth measurement model in various tasks such as classification and query is improved.

Description

technical field [0001] The present application relates to the technical field of deep learning, and in particular to an optimization method, device and storage medium of a deep metric model. Background technique [0002] In the field of deep learning, deep metric learning (Deep Metric Learning, DML) has a wide range of applications. For example, in a retrieval task based on deep learning, DML can be used to learn how to make similar features as close as possible and different features as far away as possible to improve the reliability of retrieval results. [0003] Existing metric learning methods are not easy to improve the discriminative ability of deep metric models for features. Therefore, a new solution remains to be proposed. Contents of the invention [0004] Various aspects of the present application provide an optimization method, device, and storage medium for a depth metric model, so as to improve the feature discrimination capability of the depth metric model...

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): G06K9/62G06N20/20
CPCG06N20/20G06F18/22G06F18/214
Inventor 陈炳辉
Owner ALIBABA GRP HLDG 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