Zero sample image classification method based on category attribute migration learning

A sample image, transfer learning technology, applied to computer parts, character and pattern recognition, instruments, etc., can solve the problem that the similarity cannot be directly measured, achieve the effect of simple and feasible practicality, and improve the classification accuracy

Active Publication Date: 2017-05-31
TIANJIN UNIV
View PDF2 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the visual features of samples and the semantic features of categories are located in di

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
  • Zero sample image classification method based on category attribute migration learning
  • Zero sample image classification method based on category attribute migration learning
  • Zero sample image classification method based on category attribute migration learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The invention relates to a category attribute migration learning technology for the field of zero-sample image classification. Aiming at the problem of obvious changes in the internal attributes of the category in the zero-sample image classification, it improves the traditional indirect attribute prediction method and achieves effective mining of visual samples. Deep semantic information, better prediction of attribute features of visual samples.

[0033] The purpose of the present invention is to provide a zero-shot image classification method based on category attribute transfer learning. At present, a commonly used idea in zero-shot learning is to transfer information by connecting labeled categories and unseen categories through attribute features, so as to obtain predicted semantic features of test samples. How to transfer information is one of the key technologies. Aiming at this key technology, the present invention proposes a learning framework that effectivel...

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 relates to the image processing and image classification technology, and provides an image classification technical scheme with high efficiency and accuracy; the zero sample image classification method based on category attribute migration learning comprises the following steps: building a multi-class classifier model based on attributes to determine whether a tested sample has certain attribute, wherein the model is built according to an indirect attribute prediction IAP; learning the classifications from which the attribute of the tested sample is immigrated, thus learning attributes with finer grain; carrying out transfer learning so as to realize the zero sample image classification. The IAP training phase refers to the multi-class classifier; in a test phase, the method can test the probability of the tested sample belonging to various label classifications, thus obtaining the prediction meaning characteristic of the tested sample; finally the method can use the prediction meaning characteristic to determine the unknown classification to which the tested sample belongs. The method is mainly applied to image processing.

Description

technical field [0001] The present invention relates to image processing and image classification technology, specifically, to a zero-sample image classification method based on category attribute transfer learning. Background technique [0002] For traditional image classification systems, in order to accurately identify a certain type of image, corresponding labeled training samples must be given. However, on the one hand, there are many kinds of things in the world, and it takes a lot of manpower and time to label samples; Tibetan mastiff, pug, husky, etc., and some labeled samples are difficult to obtain. In recent years, in order to solve the problem of missing samples, zero-shot learning has attracted extensive attention of researchers. The goal of zero-shot image classification is to build a classifier that can recognize images of classes that did not appear in the training data. Compared with traditional image classification methods, zero-shot image classification...

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
CPCG06F18/2415G06F18/214
Inventor 冀中孙涛
Owner TIANJIN 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