Panoramic segmentation model training method, 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, improving training efficiency and reducing workload

Active Publication Date: 2022-05-24
SHENZHEN HIVT TECH
View PDF9 Cites 0 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
  • Panoramic segmentation model training method, panoramic segmentation method and device
  • Panoramic segmentation model training method, panoramic segmentation method and device
  • Panoramic segmentation model training method, panoramic segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as recited in the appended claims.

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

[0077] At present, the training of panoramic segmentation model is usually carried out th...

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 present application provides a training method for a panoramic segmentation model, a panoramic segmentation method and a device, by respectively obtaining the first number of labeled image samples and the second number of unlabeled image samples, and updating the initial teacher network according to the labeled image samples The network parameters of the model are obtained from the teacher network model, and the network parameters of the first initial student network model in the initial panoramic segmentation model are updated according to the teacher network model and the unlabeled image samples to obtain the panoramic segmentation model. In this application, by using a small amount of labeled data and a large amount of unlabeled data to train the panoramic segmentation model, the workload of data labeling can be greatly reduced, the problem of difficult labeling of image data can be 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 an apparatus. Background technique [0002] In computer vision, image segmentation task refers to the technology and process of segmenting 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 panoptic 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 by FAIR and Heidelberg University in Germany. Its task is to assign a category Label and an instance ID to each...

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 Patents(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 Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap