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

Classification network training method and device, classification method and device and electronic equipment

A technology of classification network and training method, which is applied in the field of computer vision and can solve problems such as unbalanced training data

Active Publication Date: 2019-05-24
BEIJING SENSETIME TECH DEV CO LTD
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the classification network deals with face attribute analysis and pedestrian appearance analysis, there is a problem of unbalanced actual training data. For example, the ratio of positive and negative samples of the attribute data of baldness may be as high as 1:100. How to improve it under different training data scenarios? The performance of the trained classification network is a research hotspot in this field

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
  • Classification network training method and device, classification method and device and electronic equipment
  • Classification network training method and device, classification method and device and electronic equipment
  • Classification network training method and device, classification method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0142] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application unless specifically stated otherwise.

[0143] At the same time, it should be understood that, for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0144] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way serves as any limitation of the application, its application or uses.

[0145] Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered part...

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 classification network training method, a classification method, a classification device and electronic equipment, and the method comprises the steps: determining the sampling proportion of obtaining different types of sample images from a sample image set based on the number of sampled times corresponding to a current sample in multiple times of sampling; Based on the sampling proportion, performing current sampling on the sample image set to obtain a currently sampled sample; The classification network is trained on the basis of multiple sampling samples obtained through multiple times of sampling, the target classification network is obtained, the sample image set is sampled according to the sampling proportion dynamically changing along withthe sampling times, and the classification network obtained through training has high classification accuracy.

Description

technical field [0001] The present application relates to computer vision technology, especially a training method for a classification network, a classification method and device, and electronic equipment. Background technique [0002] Classification networks play an important role in many fields, such as pedestrian detection and tracking, large-scale smart city target task search and positioning, personal portrait description, etc. When the classification network deals with face attribute analysis and pedestrian appearance analysis, there is a problem of unbalanced actual training data. For example, the ratio of positive and negative samples of the attribute data of baldness may be as high as 1:100. How to improve it under different training data scenarios? The performance of the trained classification network is a research hotspot in this field. Contents of the invention [0003] The embodiment of the present application provides a classification network training and c...

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): G06K9/62
CPCG06N3/04G06N3/08G06F18/241G06F18/214
Inventor 甘伟豪王意如
Owner BEIJING SENSETIME TECH DEV CO LTD