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

Image annotation model training method and device and image annotation method and device

An image labeling and training method technology, applied in the computer field, can solve problems such as labor consumption, and achieve the effect of stable segmentation results

Pending Publication Date: 2021-11-19
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This may bring a lot of human consumption to the labeling work

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
  • Image annotation model training method and device and image annotation method and device
  • Image annotation model training method and device and image annotation method and device
  • Image annotation model training method and device and image annotation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The solution provided in this manual is aimed at the image target recognition business scenario. The solutions provided in this specification will be described below in conjunction with the accompanying drawings. It is worth noting that the technical solution of this application involves image processing, and some images or computer screen shots are involved in the attached drawings. In order to make the illustration more clear, the color blocks of these images have not been eliminated, and the clarity of the converted grayscale images Does not affect the expression of the essence of the program.

[0065] figure 1 An example of an application scenario of the technical architecture of this specification is shown. The application scenario is a laser pattern area recognition scenario of a document. Such as figure 1 As shown, the left side is a photo of a certificate. In order to protect data privacy, the important information of the certificate in the diagram is covere...

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 provides an image annotation model training method and device and an image annotation method and device. According to the method and the device provided by the embodiment of the invention, for the images in the training set, pixel-level labeling can be carried out through the image-level category labels. In the specific image annotation model training and image annotation process, the features of different images are subjected to cross comparison through prototype vectors, so that target areas in the images are further mined, non-target areas can be screened out, and a target segmentation task under weak supervision is achieved. In the loss determination process, not only is classification loss considered, but also the similarity between the corrected segmentation result and the original segmentation result is considered, so that the segmentation result is more stable.

Description

technical field [0001] One or more embodiments of this specification relate to the field of computer technology, and in particular, to the training of image tagging models and methods and devices for image tagging. Background technique [0002] Image processing has a wide range of applications in daily production or life. For example: laser anti-counterfeiting detection based on laser technology, document area segmentation, panorama segmentation, target recognition, etc. In these applications, weakly supervised image segmentation trained with image-level labels often results in inaccurate coverage of target regions during the generation of false ground truth values. This is because object activation maps are trained with categorical targets and lack the ability to generalize. In order to more accurately separate the target from the background, it usually involves pixel-level labeling, that is, labeling categories pixel by pixel. This may bring great human consumption to t...

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): G06K9/62G06K9/34G06K9/46G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/2155G06F18/22
Inventor 孔翔飞
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD