Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Unsupervised domain adaptation classification method based on inter-class matching

An unsupervised, domain technology that is used in instruments, character and pattern recognition, computer components, etc. to solve problems such as poor classification performance

Active Publication Date: 2017-10-20
NORTHWESTERN POLYTECHNICAL UNIV
View PDF10 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of poor classification performance of existing image classification methods between different fields, the present invention provides an unsupervised field-adaptive classification method based on inter-class matching

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
  • Unsupervised domain adaptation classification method based on inter-class matching
  • Unsupervised domain adaptation classification method based on inter-class matching
  • Unsupervised domain adaptation classification method based on inter-class matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The specific steps of the unsupervised domain adaptive classification method based on inter-class matching of the present invention are as follows:

[0055] Step 1: For a given N labeled source image field data The label representing the i-th data is For a given M unlabeled target image field data Assume for with The data have obvious distribution differences, but share a category space.

[0056] Define the sample matrix of the source image field The corresponding label vector is The sample matrix of the target image field is We aim to design a feed-forward model structure, learn the transfer characteristics of the source domain and target domain samples, and use a robust classifier to give unlabeled target domain samples X t Assign label y t . Specifically, for an unlabeled sample Learn transfer features through a mapping function f(·) Realize adaptive matching of the same category between domains. The process can be expressed as Among them, P represents the para...

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 unsupervised domain adaptation classification method based on inter-class matching, so as to solve the technical problem that the present classification method for images between different domains is poor in classification performance. According to the technical scheme, according to samples in a source image domain and a target image domain, the maximum average difference model for classes is built. A linear projection method is used to build a feature representation model for domain migration, the source domain samples and the target domain samples are projected to the same hidden feature space. In joint consideration of the supervision information of the source domain samples and hidden low-rank structural features between samples in the target domain, a robust target domain classification model is built, and all unlabeled samples in the target domain are marked. A joint optimization model with minimization of the distribution difference of the same class between domains as a target is built, an alternating minimization optimization method is used, alternating iteration of the feature representation model and the classification model is carried out until convergence, the optimal target domain classification result is obtained finally, and the classification performance is good.

Description

Technical field [0001] The present invention relates to an image classification method between different fields, in particular to an unsupervised field adaptive classification method based on matching between classes. Background technique [0002] With the proliferation of visual data, computer vision usually faces a situation where the feature distribution of the source image field (training data) does not match the feature of the target field (test data). The domain adaptation method aims to reduce the performance loss of applying the classifier trained in the source domain to the target domain. Among them, the most challenging task is the unsupervised domain adaptation method. All samples in the target domain are sample-free. In order to effectively eliminate the distribution differences between domains, most methods mainly describe data characteristics in different domains. , Trying to minimize the difference between the global domain feature distribution. [0003] The docume...

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
CPCG06F18/285G06F18/241G06F18/214
Inventor 魏巍张艳宁张磊张锦阳
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products