Semantic segmentation model training method and device, equipment and medium

A semantic segmentation and training method technology, applied in the computer field, can solve the problems of time-consuming and labor-intensive, increasing the pressure of data labeling, etc., to achieve the effect of reducing pressure, reducing dependence, and ensuring training effect

Pending Publication Date: 2022-01-25
JINGDONG KUNPENG (JIANGSU) TECH CO LTD
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The pixel-level label data that the existing semantic segmentation model relies on for training requires manual labeling of the semantic label corresponding to each pixel in the sample image, which is time-consuming and laborious, and greatly increases the pressure of data labeling

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 method and device, equipment and medium
  • Semantic segmentation model training method and device, equipment and medium
  • Semantic segmentation model training method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] figure 1 It is a flow chart of a semantic segmentation model training method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of training a semantic segmentation model. The method can be executed by a semantic segmentation model training device, which can be realized by software and / or hardware, and integrated in electronic equipment. Such as figure 1 As shown, the method specifically includes the following steps:

[0036] S110. Based on the first sample image and the image category label corresponding to the first sample image, train the first semantic segmentation model.

[0037] Wherein, the first sample image may include a positive sample image and a negative sample image, the positive sample image may refer to a sample image in an application scene, and the negative sample image may be a sample image completely irrelevant to the application scene. For example, in an automatic driving scene, the scene image in the ...

Embodiment 2

[0055] figure 2 It is a flowchart of a semantic segmentation model training method provided by Embodiment 2 of the present invention. On the basis of the above-mentioned embodiments, this embodiment details the training process of the first semantic segmentation model and the second semantic segmentation model. describe. The explanations of terms that are the same as or corresponding to the above-mentioned embodiments will not be repeated here.

[0056] see figure 2 , the training method of the semantic segmentation model provided by the present embodiment has the following steps:

[0057] S210. Input the first sample image into the first semantic segmentation model, and determine the probability value that each first pixel in the first sample image is predicted to be each semantic label according to the output of the first semantic segmentation model, Wherein, the semantic labels include: a first semantic label identical to the image category label corresponding to the f...

Embodiment 3

[0090] Image 6 It is a flow chart of a training method for a semantic segmentation model provided by Embodiment 3 of the present invention. On the basis of the above-mentioned embodiments, this embodiment "uses the second semantic segmentation model after training as the target semantic segmentation model" Optimized. The explanations of terms that are the same as or corresponding to the above-mentioned embodiments will not be repeated here.

[0091] see Image 6 , the training method of the semantic segmentation model provided by the present embodiment has the following steps:

[0092] S610. Train the first semantic segmentation model based on the first sample image and the image category label corresponding to the first sample image.

[0093] S620. Input the second sample image into the first semantic segmentation model after training, and obtain the first pixel semantic label corresponding to the second sample image according to the output of the first semantic segmentat...

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 embodiment of the invention discloses a semantic segmentation model training method and device, equipment and a medium. The method comprises the following steps: training a first semantic segmentation model based on a first sample image and an image class label corresponding to the first sample image; inputting a second sample image into the trained first semantic segmentation model, and obtaining a first pixel semantic tag corresponding to the second sample image according to the output of the trained first semantic segmentation model; based on a saliency map corresponding to the second sample image, correcting the first pixel semantic tag, and determining a corrected second pixel semantic tag; and training the second semantic segmentation model based on the second sample image and the second pixel semantic tag, and taking the trained second semantic segmentation model as a target semantic segmentation model. Through the technical scheme of the embodiment of the invention, the dependence of the semantic segmentation model on dense annotation data can be reduced, and the pressure of data annotation is reduced.

Description

technical field [0001] The embodiments of the present invention relate to computer technology, and in particular to a training method, device, equipment and medium for a semantic segmentation model. Background technique [0002] With the rapid development of computer technology, the semantic segmentation model based on deep learning can be used to segment the image at the pixel level to determine the object category to which each pixel in the image belongs, thereby improving the image segmentation effect. [0003] At present, before using the semantic segmentation model, the semantic segmentation model is usually trained using the pixel-level label data corresponding to the sample image, so that the semantic segmentation model after training can accurately perform image segmentation operations. [0004] However, in the course of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: [0005] The pixel-level label...

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): G06V10/25G06V10/26G06N3/04
CPCG06N3/045
Inventor 徐鑫
Owner JINGDONG KUNPENG (JIANGSU) TECH CO LTD
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