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

Feature learning method, target object identification method and corresponding device

A target object and feature learning technology, applied in the field of image recognition, can solve the problem of inaccurate image feature extraction, and achieve the effect of narrowing the gap, reducing the correlation, and improving the accuracy

Pending Publication Date: 2021-11-26
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present application provides a feature learning method, a target object recognition method and a corresponding device to solve the problem of inaccurate image feature extraction of objects in the prior art

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
  • Feature learning method, target object identification method and corresponding device
  • Feature learning method, target object identification method and corresponding device
  • Feature learning method, target object identification method and corresponding device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0099] Optionally, in another embodiment of the present application, an implementation manner of step S102 may include:

[0100] Using the formula for minimizing the intra-class distance of the third loss function, the feature vector of the target object is calculated to obtain a third loss value.

[0101] The fourth loss value is obtained by calculating the feature vector of the target object by using the calculation formula of reducing the intra-class distance by orthogonalization of the third loss function.

[0102] Specifically, the eigenvector of the target object is substituted into the calculation formula for minimizing the intra-class distance of the center loss function to obtain the third loss value, which is used to represent the gap between the image sample and the class center corresponding to the category to which the image sample belongs. The specific formula is as follows :

[0103]

[0104] Among them, L intra is the third loss value, v i Is the feature ...

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 feature learning method, a target object recognition method and a corresponding device, which are applied to the technical field of image recognition. The feature vector extraction model is obtained by training a neural network model based on a first loss value and a second loss value corresponding to a feature vector of a target object contained in an image sample, and the first loss value represents a difference between the image sample and a class center corresponding to a class to which the image sample belongs; the second loss value represents correlation between class centers corresponding to classes to which different image samples belong; therefore, the neural network model is trained through the first loss value and the second loss value, so that when the feature vector extraction model obtained through training performs feature vector extraction of the target object on the image, the difference between the image and the class center corresponding to the class to which the image belongs can be reduced; moreover, the correlation between the class centers corresponding to the classes to which different images belong is reduced, and the accuracy of carrying out the feature vector of the target object on the image by the feature vector extraction model is improved.

Description

technical field [0001] The present application relates to the technical field of image recognition, and in particular to a feature learning method, a target object recognition method and a corresponding device. Background technique [0002] In recent years, with the emergence of a large number of short videos in Shanghai on social media platforms, the platform has an increasing demand for user portrait description, content recommendation and review. Object recognition, as one of the important information in video understanding, has attracted more and more attention. Concern, such as face recognition. However, compared with object recognition on pictures, short videos shot and uploaded by users on social platforms generally have problems such as jitter, blur, strong lighting changes, and complex scene changes, which also brings greater challenges to object recognition on short videos. challenge. [0003] In the object recognition process, object image feature extraction is ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 曹琼车翔
Owner TENCENT TECH (SHENZHEN) CO LTD