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

Semantic segmentation model training and image segmentation method and device, and calculating equipment

A technology for semantic segmentation and training images, applied in the field of computer vision, which can solve problems such as time-consuming

Active Publication Date: 2017-03-22
BEIJING SENSETIME TECH DEV CO LTD
View PDF2 Cites 92 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Semantic segmentation is usually very time-consuming because of its annotation data requiring pixel-level annotation

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
  • Semantic segmentation model training and image segmentation method and device, and calculating equipment
  • Semantic segmentation model training and image segmentation method and device, and calculating equipment
  • Semantic segmentation model training and image segmentation method and device, and calculating equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0073] In the process of realizing the present invention, the inventor found that there are some semi-supervised or weakly supervised methods to train semantic segmentation problems by studying the prior art. Traditional weakly supervised semantic segmentation for a given image category usually falls into two categories. The first type is to directly predict the pixel category by using a multiple instance learning (Multiple Instanc...

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 semantic segmentation model training and image segmentation method and device, and calculating equipment, and belongs to the technical field of computer vision. The method comprises the steps: inputting a training image to a semantic segmentation model, and obtaining the preliminary result of semantic segmentation of the training image outputted by the semantic segmentation model; carrying out the fusion of local candidate regions according to the weak supervision information and the local candidate regions selected from the training image, and obtaining a correction result of semantic segmentation of the training image; correcting the parameters of the semantic segmentation model according to the preliminary result and a correction result; carrying out the iteration of the training steps till the training result of the semantic segmentation model meets a preset convergence condition. According to the scheme of the invention, the method achieves the direct supervision at the pixel level, also can optimize the semantic segmentation model in an end-to-end manner, and also can improve the result of segmented branches according to the judgment of the local candidate regions.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a semantic segmentation model training method and device based on weak supervision, a computing device, and an image segmentation method and device. Background technique [0002] Semantic segmentation is a classic problem in the field of computer vision. The purpose is to predict the object category of each pixel of the input image and achieve accurate and dense pixel-level understanding of the image. Semantic segmentation is usually time-consuming because of the pixel-level annotations required for labeled data. According to the practical experience of common methods, it usually takes 5-8 minutes to obtain an accurate semantic segmentation annotation with a size of 400*600 pixels. Therefore, the speed and quality of data annotation has become an important issue that restricts the problem from obtaining big data support and further development. Contents of the ...

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): G06T7/11G06T7/194G06T7/136
Inventor 石建萍
Owner BEIJING SENSETIME TECH DEV CO LTD
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