Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Training method and device of panoramic segmentation model and panoramic segmentation method and device

A technology of segmentation model and training method, applied in the field of image processing, can solve the problem of difficult labeling of image data, and achieve the effect of solving difficult labeling, reducing workload and improving training efficiency

Active Publication Date: 2022-02-18
SHENZHEN HIVT TECH
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present application provides a training method for a panoramic segmentation model, a panoramic segmentation method and a device, which are used to solve the problem that image data is difficult to label in the prior art, thereby improving the training efficiency of the panoramic segmentation model

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
  • Training method and device of panoramic segmentation model and panoramic segmentation method and device
  • Training method and device of panoramic segmentation model and panoramic segmentation method and device
  • Training method and device of panoramic segmentation model and panoramic segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

[0076] The technical solution provided by the embodiment of the present application may be applied to a scene where a picture is panoramically segmented. For example, by performing panoramic segmentation on the picture, the occluded part of the picture can be restored or the target can be identified.

[0077] At present, the training of panoramic segmentation models is usually carried o...

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 training method and device of a panoramic segmentation model, and a panoramic segmentation method and device. The training method comprises the steps: obtaining a first number of labeled image samples and a second number of unlabeled image samples, updating the network parameters of an initial teacher network model according to the labeled image samples, obtaining a teacher network model, and according to the teacher network model and the label-free image sample, updating network parameters of a first initial student network model in the initial panoramic segmentation model to obtain a panoramic segmentation model. According to the invention, the panoramic segmentation model is trained by using a small amount of label data and a large amount of unlabeled data, so that the workload of data labeling can be greatly reduced, the problem that the image data is difficult to label is solved, and the training efficiency of the panoramic segmentation model can be improved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a training method for a panoramic segmentation model, a panoramic segmentation method and a device. Background technique [0002] In computer vision, the task of image segmentation refers to the technology and process of dividing an image into several specific and unique regions according to certain rules, and extracting objects of interest. Currently, image segmentation tasks have been developed into the following subfields: semantic segmentation, instance segmentation, and the emerging field of panoramic segmentation. The task of image semantic segmentation is to predict the semantic category of each pixel; the task of instance segmentation is to predict the pixel area contained in each instance object. Panoramic segmentation was first proposed jointly by FAIR and Heidelberg University in Germany. Its task is to assign a category Label and instance ID to...

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): G06V10/26G06V10/774G06K9/62
CPCG06F18/214
Inventor 周波蔡芳发苗瑞邹小刚
Owner SHENZHEN HIVT TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com