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

Semantic enhanced hash method for zero-sample image retrieval

A sample image and semantic technology, applied in the computer field, to achieve the effect of improving accuracy, reducing storage overhead, and improving retrieval speed

Active Publication Date: 2020-06-12
DALIAN UNIV OF TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Semantic alignment can make the model have generalization ability, can learn knowledge from visible class data, and generalize to unseen classes to solve the zero-sample problem

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
  • Semantic enhanced hash method for zero-sample image retrieval
  • Semantic enhanced hash method for zero-sample image retrieval
  • Semantic enhanced hash method for zero-sample image retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0022] figure 1 It is the overall frame diagram of the present invention. It can be seen from the figure that the subject flow of the present invention is as follows: firstly, the visual features of the image are projected into the category semantic space to improve discrimination; secondly, a mapping from the category semantic space to the binary code is learned; not only that, combined with the domain structure Information retention and supervised label information, reverse regression label information to binary encoding, and discretely learn binary encoding; finally learn a hash function to handle new data out of the sample.

[0023] Specific steps are as follows:

[0024] A semantically enhanced hashing method for zero-shot image retrieval, the semantically enhanced hashing method adopts linear projection with bias, including the following steps: ...

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

A semantic enhanced hash method for zero-sample image retrieval belongs to the technical field of computers and comprises the following steps: 1) performing image feature semantic alignment; 2) maintaining a domain structure; 3) hash code learning; 4) constructing and optimizing a total objective function; and 5) hash function learning for new data. The method mainly aims at solving the problem oflarge-scale image retrieval, and due to the fact that large-scale image data is generated from the Internet, for some newly-generated affairs and new categories, it is difficult for an existing algorithm to collect enough training pictures of new affairs to train a retrieval model. Therefore, the category semantic space is used as the middle transition space between the image visual features andthe binary codes, alignment of the visual space and the category semantic space is achieved, and the purpose of migrating knowledge from visible data to invisible data is achieved. Experimental verification shows that knowledge can be effectively learned from visible data and migrated to an invisible class, and the problem of zero-sample image retrieval is solved.

Description

technical field [0001] The invention belongs to the technical field of computers and relates to a semantically enhanced hashing method for zero-sample image retrieval. Background technique [0002] In recent years, hashing technology has been widely researched and applied in large-scale image and video retrieval due to its advantages in reducing storage overhead and speeding up retrieval. Hash technology encodes high-dimensional image and video data into a concise binary coded form, or a discrete coded form, usually represented by 0 and 1, which is also in line with the storage form of data in computer memory. In this way, the retrieval can be performed in the Hamming space composed of binary codes, and the retrieval speed can be greatly improved through the exclusive-or bit operation between the codes. The key to hashing technology is to learn hash functions and binary encoding. [0003] Much existing work is dedicated to designing novel hashing methods, where early data-...

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 Applications(China)
IPC IPC(8): G06F16/55G06F16/583G06F16/51G06F16/53G06N3/08
CPCG06N3/08G06F16/51G06F16/53G06F16/55G06F16/583
Inventor 钟芳明陈志奎王光泽张雯珺
Owner DALIAN UNIV OF TECH
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