Unlock instant, AI-driven research and patent intelligence for your innovation.

Detection model updating method and device and storage medium

A detection model and technology to be detected, applied in the field of deep learning, can solve the problems of reduced detection accuracy, outdated training data, and insufficient training data, and achieve the effect of improving detection accuracy

Pending Publication Date: 2020-11-10
HANGZHOU HIKVISION DIGITAL TECH
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complex and changeable environment, media information, or other human factors, the training data may be outdated or insufficient. If you continue to use the detection model trained before, the detection accuracy may be reduced, or it may not meet user expectations. Therefore, it is necessary to Continuously update and optimize the deployed detection model to ensure detection accuracy and other indicators

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
  • Detection model updating method and device and storage medium
  • Detection model updating method and device and storage medium
  • Detection model updating method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will further describe the embodiments of the present application in detail in conjunction with the accompanying drawings.

[0060] At present, detection models based on deep learning technology are widely used in various scenarios, such as video surveillance, audio surveillance, text recognition, data trend prediction and other scenarios. Among them, the deployed detection model is obtained through supervised learning training based on the training data with accurate labels, and due to the complex and changeable environment, media information, or other human factors, this part of the training data may be outdated or insufficient. If you continue to use the previously trained detection model, the detection accuracy may decrease, or the detection accuracy may not meet user expectations. Therefore, it is necessary to continuously update and o...

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 detection model updating method and device and a storage medium, and belongs to the technical field of deep learning. In the embodiment of the invention, the first training data set is determined according to the feedback information of the user for the detection result, and the determined first training data set is used as the supplementary material andoptimizes and updates the detection model together with the training data comprising the corresponding accurate label, namely, the detection model is optimized and updated together with the trainingdata comprising the corresponding accurate label. The detection model can be automatically optimized and updated, and the detection accuracy of the detection model is improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of deep learning, and in particular to a method, device and storage medium for updating a detection model. Background technique [0002] At present, detection models based on deep learning technology are widely used in various scenarios, such as video surveillance, audio surveillance, text recognition, data trend prediction and other scenarios. Among them, the deployed detection model is based on training with accurate labels. The data is obtained through supervised learning training. However, due to the complex and changeable environment, media information, or other human factors, the training data may be outdated or insufficient. If you continue to use the detection model trained before, the detection accuracy may be reduced, or it may not meet user expectations. Therefore, it is necessary to Continuously update and optimize the deployed detection model to ensure detection accu...

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): G06N20/00G06N3/08
CPCG06N20/00G06N3/08
Inventor 张迪
Owner HANGZHOU HIKVISION DIGITAL TECH