Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Cross-supervised model training method, image segmentation method and related equipment

A technology for model training and image segmentation, applied in the field of image processing, can solve the problems of inability to guarantee the accuracy of model operation and difficulty in labeling, and achieve the effect of reducing labeling and improving accuracy.

Pending Publication Date: 2022-07-12
ZHEJIANG DAHUA TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, when training network models such as segmentation models and classification models, it is necessary to manually label a large number of sample data. When labeling pixel-level labels is required, a lot of labeling resources are required, and labeling is difficult. When the number of labeled samples is small , the calculation accuracy of the trained model cannot be guaranteed

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
  • Cross-supervised model training method, image segmentation method and related equipment
  • Cross-supervised model training method, image segmentation method and related equipment
  • Cross-supervised model training method, image segmentation method and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the purpose, technical scheme and effect of the present invention clearer and clearer, the present invention will be described in further detail below with reference to the accompanying drawings and examples.

[0028] The present application provides a cross-supervised model training method. By establishing a twin network, the output results of the two networks are respectively used as the training labels of the other network for training. Using the cross-supervised method can reduce the labeling of initial sample images. Improve the accuracy of model operations.

[0029] see figure 1 , figure 1 It is a schematic flowchart of an embodiment of the model training method of the present application. It should be noted that if there are substantially the same results, this embodiment does not figure 1 The sequence of processes shown is limited. like figure 1 As shown, this embodiment includes:

[0030] S110: Acquire a sample image.

[0031] S130: Inpu...

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 discloses a cross-supervised model training method, an image segmentation method and related equipment. The cross-supervised model training method comprises the following steps: acquiring a sample image; the sample image is input into a basic twin network, the twin network comprises a first network and a second network which are the same in network structure, and basic parameters of the first network are different from basic parameters of the second network; calculating the loss of the second network by taking the prediction result of the first network as the label of the second network, and calculating the loss of the first network by taking the prediction result of the second network as the label of the first network so as to obtain the loss of the twin network; iteratively updating the parameters of the first network and the second network based on the loss of the twin network until a training cut-off condition is met; and taking the trained and updated first network or second network as a target model. By means of the mode, annotation of the sample images can be reduced, and the model operation accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a cross-supervised model training method, an image segmentation method and related equipment. Background technique [0002] At present, when training network models such as segmentation models and classification models, a large amount of sample data needs to be manually labeled. When pixel-level labels need to be labeled, a lot of labeling resources are required, and labeling is difficult, and when the number of labeled samples is small. , the operational accuracy of the model obtained by training cannot be guaranteed. SUMMARY OF THE INVENTION [0003] The main technical problem solved by the present invention is to provide a cross-supervised model training method, an image segmentation method and related equipment, which can reduce the labeling of sample images and improve the accuracy of model operation. [0004] In order to solve the above technical problem, a tech...

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): G06K9/62G06N3/08G06T7/10G06V10/764G06V10/774G06V10/80
CPCG06N3/08G06T7/10G06F18/214G06F18/241G06F18/254
Inventor 林春晖熊剑平
Owner ZHEJIANG DAHUA TECH CO LTD
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
Eureka Blog
Learn More
PatSnap group products