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

An application method of zero-order learning based on correlated double autoencoder

A self-encoder and encoded technology, applied in image encoding, instruments, computer parts, etc., can solve the problem of feature redundancy, and achieve the effect of good classification and recognition accuracy.

Active Publication Date: 2020-08-25
HANGZHOU DIANZI UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, if the category span is relatively large, there will be feature redundancy

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
  • An application method of zero-order learning based on correlated double autoencoder
  • An application method of zero-order learning based on correlated double autoencoder
  • An application method of zero-order learning based on correlated double autoencoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with drawings and embodiments.

[0051] Such as figure 1 As shown, a method based on correlation double autoencoder in zero-shot learning includes the following steps:

[0052] Step (1) obtains the encoded visual features;

[0053] Step (2) obtains the optimized semantic feature;

[0054] Step (3) maps the optimized semantic features to visual features;

[0055] Step (2) is obtained by the following steps: as figure 2 As shown, step A establishes an autoencoder for semantic features, adds the encoded visual features obtained in step (1) to the encoded semantic features, and then decodes the added semantic features; step B The semantic features obtained after decoding are added to the original semantic features to obtain better and more complete semantic features.

[0056] The technical scheme further defined in the present invention is:

[0057]Step (1) is specifically: process the visual featur...

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 application method in zero-order learning based on a correlation double autoencoder. The present invention establishes autoencoders for visual features and semantic features respectively. But these two autoencoders are not independent, they are connected. We add the encoded visual features to the encoded semantic features, and then decode the added semantic features. Finally, the decoded semantic features are added to the original semantic features to obtain better and more complete semantic features. The optimized semantic features are then mapped to visual features for classification and recognition. The present invention optimizes the semantic features by using the correlation double autoencoder model to obtain more distinguishable and finer-grained semantic features. The optimized semantic features obtained in this way are then mapped to the visual feature space, which can achieve better classification and recognition accuracy.

Description

technical field [0001] The invention uses a correlation double autoencoder for zero-time learning, belongs to the technical field of zero-time learning, and specifically relates to an application method based on a correlation double autoencoder for zero-time learning. Background technique [0002] In the existing research on zero-shot learning, more attention is paid to the mapping relationship between the visual features of the image and the semantic features of each class. However, the features themselves also have an important impact on the final classification recognition. Especially semantic features, some similar categories, their feature representations are very close, and the distinction between categories is not great. In addition, if the category span is relatively large, there will be feature redundancy. Therefore, it is of great significance to construct more discriminative and finer-grained semantic features. Contents of the invention [0003] In order to c...

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): G06T9/00G06K9/46G06K9/62
CPCG06T9/002G06T2207/20081G06T2207/20084G06V10/48G06F18/24
Inventor 姜明刘志勇张旻汤景凡吴俊磊
Owner HANGZHOU DIANZI 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com