A semi-supervised image instance segmentation method based on stepwise adversarial learning

A semi-supervised, image-based technology, applied in image analysis, image data processing, instruments, etc., can solve technical difficulties and other problems, achieve the effect of reducing workload and improving segmentation performance

Active Publication Date: 2019-06-28
SOUTHEAST UNIV
View PDF6 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, for the problem of semi-supervised image instance segmentation, there are still great technical difficulties and challenges

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
  • A semi-supervised image instance segmentation method based on stepwise adversarial learning
  • A semi-supervised image instance segmentation method based on stepwise adversarial learning
  • A semi-supervised image instance segmentation method based on stepwise adversarial learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the object, technical solution and advantages of the present invention clearer, the specific implementation cases of the present invention will be described below in conjunction with the accompanying drawings.

[0036] The invention discloses a semi-supervised image instance segmentation method based on step-by-step adversarial learning, such as figure 1 shown, including the following steps:

[0037] Step 1. Collect multiple image samples to be segmented, and label some of them to obtain the labeled data set {X l , Y l}, where X l represents a collection of images, Y l Represents a mask label set; unlabeled samples form an unlabeled data set X u ;

[0038] Build an instance segmentation model, the instance segmentation model is Mask R-CNN, its structure is as follows figure 2 As shown, its backbone network is the feature pyramid network FPN; Mask R-CNN also includes the region generation network RPN, RolAlign, and deconvolution network Deconv; 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 invention discloses a semi-supervised image instance segmentation method based on stepwise adversarial learning. The semi-supervised image instance segmentation method comprises the steps of 1, constructing Mask R-CNN instance segmentation model; 2, Training FPN in a Mask R-CNN Based on DCGAN; 3, adopting labeled data to perform preliminary training on other modules in the Mask R-CNN; 4, constructing a discriminant convolutional network, and forming an adversarial learning network with the Mask R-CNN, and optimizing parameters of the adversarial learning network through adversarial training; 5, feeding back the output of the discriminative convolutional network to Mask R-CNN for retraining the instance segmentation model; And 6, segmenting the to-be-segmented image by using the instance segmentation model. According to the method, the sample set only partially labeled with the image is used for model training, the workload of sample processing is reduced, and a segmentation model with high precision can be obtained.

Description

technical field [0001] The invention relates to the field of image instance segmentation, in particular to an image semi-supervised instance segmentation method based on step-by-step confrontation learning. Background technique [0002] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. It is a key step from image processing to image analysis. Deep learning technology automatically learns more effective image feature expression from massive data, and is successfully used for image detection and segmentation of general objects. However, there are still huge difficulties and challenges in applying deep learning methods to image detection and segmentation for specific tasks. Challenge: Existing target instance segmentation methods require that all training instances must be labeled with a segmentation mask, making annotating new categories prohibitively expensive. The pre...

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): G06T7/11G06N3/04
Inventor 马家乐钱堃刘睿段彦卉景星烁
Owner SOUTHEAST UNIV
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