Cross-domain semantic segmentation method based on graph convolution and contrast learning

A semantic segmentation and convolution technology, applied in the field of pattern recognition and computer vision, can solve the problems of difficult migration of category proportion distribution, poor cross-domain effect, imbalanced distribution of different categories, etc., to achieve excellent evaluation results and improve class imbalance. Effect

Pending Publication Date: 2022-01-07
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a cross-domain semantic segmentation method based on graph convolution and comparative learning, which is used to solve the problem of unbalanced distribution of different categories in the existing segmentation methods, the distribution of categories with a small proportion is difficult to migrate, and the cross-domain effect is relatively poor problem, the present invention realizes the goal of transfer learning

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-domain semantic segmentation method based on graph convolution and contrast learning
  • Cross-domain semantic segmentation method based on graph convolution and contrast learning
  • Cross-domain semantic segmentation method based on graph convolution and contrast learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Embodiment 1: as Figure 1-Figure 3 As shown, the cross-domain semantic segmentation method based on graph convolution and contrastive learning, the specific steps of the method are as follows:

[0059] S1: Select a network training data set, the network training data set includes a source domain data set and a target domain data set, wherein the source domain data set contains labels, and the target domain data set does not contain labels; the target domain data set includes training data sets and test set;

[0060] S2: Construct the basic network model for semantic segmentation. First, use the source domain dataset to train the basic network model for semantic segmentation. Use the basic network model for semantic segmentation trained by the source domain dataset as the basic network, and combine the source domain dataset and the target domain dataset together. sent to the basic network for training;

[0061] S3: Use the feature map output by the middle layer of the...

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 cross-domain semantic segmentation method based on graph convolution and contrast learning, and belongs to the field of transfer learning and computer vision. The invention designs a method for solving an adjacent matrix in different domains, and provides a new thought for establishing a long-distance context relationship between the domains. In order to solve the problem of unbalanced distribution of different categories, learning loss is grouped and compared. Secondly, in order to extract domain-invariant information, a newly proposed double-domain adjacent matrix is utilized to perform graph convolution operation; in the process of graph convolution operation, a graph structure is constructed on a feature graph, and in order to establish a long-distance context relationship between domains, the graph convolution operation is creatively completed in the proposed graph structure by using the proposed double-domain adjacent matrix. According to the method provided by the invention, a long-distance context relationship between domains is established, domain-invariant information can be extracted more effectively, and a better evaluation result is obtained in subjective and objective evaluation.

Description

technical field [0001] The invention designs a cross-domain semantic segmentation method based on graph convolution and comparative learning, which belongs to the field of pattern recognition and computer vision. Background technique [0002] The basic task of semantic segmentation is to correctly classify each pixel in the image. Since semantic segmentation is a classification task at the pixel level, it is very helpful for scene understanding tasks, so semantic segmentation tasks have broad development prospects in tasks such as autonomous driving, medical image segmentation, and scene recognition. [0003] Since the advent of fully convolutional networks, convolutional neural networks have made great progress in the field of semantic segmentation. However, since the semantic segmentation task requires pixel-level labels during the training process, and labeling pixel-level labels requires a lot of manpower and material resources, people consider using synthetic datasets ...

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): G06V20/70G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2415
Inventor 谢明鸿赵伟枫张亚飞
Owner KUNMING UNIV OF SCI & 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