Difficulty sample sampling method and system

A sample and number of samples technology, applied in the field of difficult sample sampling methods and systems, can solve problems such as slow speed and difficult sample mining methods, and achieve the effect of improving speed, ensuring detection accuracy and timeliness

Active Publication Date: 2019-07-05
开易(北京)科技有限公司
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the two-stage method based on preselection box screening is too slow, and there is no more effective difficult sample mining method on the one-stage method based on direct regression

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
  • Difficulty sample sampling method and system
  • Difficulty sample sampling method and system
  • Difficulty sample sampling method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

[0054] The following will be combined with figure 1 And attached figure 2 , the difficult sample sampling method provided by the embodiment of the present invention is introduced in detail.

[0055] See figure 1 , which provides a schematic flowchart of a difficult sample sampling method for an embodiment of the present invention. Such as figure 1 As shown, the method in the embodiment of the present invention may include the following steps S101-S103.

[0056] S101. Obtain a feature map corresponding to the input training image data by using a deep learning model.

[0057] Specifically, the sampling system can use a deep learning model to obtain the feature map corresponding to the input training image data. It can be understood that the above deep learning model can be...

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 difficult sample sampling method and system. The method comprises the following steps: obtaining a feature map corresponding to input training image data byadopting a deep learning model, then determining the number of difficult samples in the feature map based on a first hyper-parameter, and then calculating a preset number of difficult samples in thefeature map according to a second hyper-parameter and samples in the feature map. By the adoption of the method and device, the speed of difficult sample mining can be increased by introducing the twohyper-parameter analysis characteristic graphs, then the characteristic graphs are processed on the basis of the HES model, the parameters of the target detection model are updated, and the final detection precision and timeliness can be guaranteed.

Description

technical field [0001] The invention relates to the technical field of sample mining, in particular to a difficult sample sampling method and system. Background technique [0002] In the process of machine learning model training, samples with weak model recognition ability are set as hard samples. Mining learning on hard samples can significantly improve the detection accuracy of object detection methods. However, the two-stage method based on preselection box screening is too slow, and there is no more effective difficult sample mining method on the one-stage method based on direct regression. Contents of the invention [0003] The embodiment of the present invention provides a difficult sample sampling method and system. By introducing two hyperparameters to analyze the difficult samples in the feature map, the speed of difficult sample mining can be improved, and then the feature map is processed based on the HES model, and the target detection model is updated. The ...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/214
Inventor 祁亚斐刘鹏左思
Owner 开易(北京)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap