Image processing method, electronic device and computing storage medium

An image processing and image technology, applied in computing, computer components, instruments, etc., can solve problems such as high labeling costs, poor performance of image classification models, and limited images

Active Publication Date: 2022-05-13
ZTE CORP +1
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, due to various reasons such as high annotation cost and sensitivity, the annotated images are often very limited, which leads to poor performance of image classification models

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
  • Image processing method, electronic device and computing storage medium
  • Image processing method, electronic device and computing storage medium
  • Image processing method, electronic device and computing storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0028] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0029] The terminology used herein is for describing particular embodiments only and is not intended to limit the present disclosure. As used herein, the singular forms "a" and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that when the terms "comprising" and / or "consisting of" are used in this specification, the stated features, integers, steps, operations, elements and / or co...

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 disclosure provides an image processing method, including: determining the feature representation performance parameters and information amount parameters of each image in the unlabeled image set; according to the feature representation performance parameters and information amount parameters of each image in the unlabeled image set Selecting a target image that meets the image validity requirement from the set of unlabeled images, and labeling the target image. It can take into account the performance of images in feature learning and the information content of images for downstream tasks, automatically select efficient images for labeling, reduce the cost of labeling and help improve the performance of image classification models. The present disclosure also provides an electronic device and a computer storage medium.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an image processing method, an electronic device and a computer storage medium. Background technique [0002] Self-supervised learning is an important technique for image feature representation learning, which learns feature representations from large-scale unlabeled images without using any human annotations. After image feature representation learning, the image classification model still needs to be fine-tuned on the labeled images to achieve image classification tasks. At present, due to various reasons such as high annotation cost and sensitivity, annotated images are often very limited, which leads to poor performance of image classification models. Contents of the invention [0003] The present disclosure aims at the above-mentioned deficiencies in the prior art, and provides an image processing method, an electronic device, and a computer storage medium...

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): G06V10/764G06V10/774G06K9/62
CPCG06F18/24G06F18/214
Inventor 周慧屠要峰周祥生孙康康黄圣君
Owner ZTE CORP
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