Image classification model processing method and device, and storage medium

A classification model and processing method technology, applied in the field of image recognition, can solve problems such as difficulty in effectively improving the accuracy of image classification models

Active Publication Date: 2018-11-27
MIGU CO LTD +1
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the embodiment of the present invention expects to provide a processing method, device and storage medium of an image classific

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 classification model processing method and device, and storage medium
  • Image classification model processing method and device, and storage medium
  • Image classification model processing method and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to understand the characteristics and technical contents of the embodiments of the present invention in more detail, the implementation of the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the present invention.

[0031] figure 2 An optional implementation flowchart of the image classification model processing method provided by the embodiment of the present invention, the image classification model processing method can be applied to a server or a terminal device; figure 2 As shown, the implementation process of the image classification model processing method in the embodiment of the present invention may include the following steps:

[0032] Step 201: Map the image samples in the source domain and the image samples in the target domain in the original space to the same feature space, corresponding...

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 an image classification model processing method. The image classification model processing method comprises the following steps: mapping source domain image samples and targetdomain image samples in an original space to the same characteristic space, and correspondingly obtaining the mapped source domain image samples and the mapped target domain image samples; performingdimensionality reduction on the mapped source domain image samples and the mapped target domain image samples, and correspondingly obtaining a source domain subspace and a target domain subspace; aligning samples in the source domain subspace and the target domain subspace, and determining reduced-dimension source domain image samples when a distribution difference between a source domain and a target domain in the characteristic space satisfies a preset minimum difference condition; performing weighting processing on each type of samples in the reduced-dimension source domain image samples, and obtaining aligned and weighted source domain image samples; applying the aligned and weighted source domain image samples and corresponding label information to a model for classifying new image samples in the target domain. The invention also discloses an image classification model processing device and a storage medium.

Description

technical field [0001] The invention relates to image recognition technology in the computer field, in particular to a processing method, device and storage medium of an image classification model. Background technique [0002] Currently, there is an important assumption in conventional machine learning that the sample data of the source domain (also called training data) has the same distribution as the sample data of the target domain (also called test data). However, in many practical applications, this assumption often does not hold. Therefore, the recognition effect of the image classification model trained by traditional image recognition methods is far from meeting people's expectations. [0003] In fact, when the sample data in the source domain and the sample data in the target domain cannot meet the condition of the same distribution, domain adaptive methods such as unsupervised domain adaptive methods can be used to classify image samples. Currently, in related ...

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): G06K9/62
CPCG06F18/213G06F18/24G06F18/214
Inventor 许明微李琳吴耀华
Owner MIGU 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