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

Weakly-supervised depth context-aware image characterization method and weak-supervised depth context-aware image characterization system

A contextual and weakly supervised technology, applied in the field of weakly supervised deep context-aware image representation, to achieve the effect of enhancing distinction, enhancing discrimination, and improving quality

Active Publication Date: 2021-04-16
SHANDONG JIANZHU UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, weakly supervised deep image hashing representation learning is still in its infancy and remains to be further explored

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
  • Weakly-supervised depth context-aware image characterization method and weak-supervised depth context-aware image characterization system
  • Weakly-supervised depth context-aware image characterization method and weak-supervised depth context-aware image characterization system
  • Weakly-supervised depth context-aware image characterization method and weak-supervised depth context-aware image characterization system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] This embodiment provides a weakly supervised deep context-aware image representation method;

[0037] Such as figure 1 As shown, a weakly supervised deep context-aware image representation method, including:

[0038] S101: Acquiring images to be processed;

[0039] S102: Perform representation extraction on the image to be processed to extract a basic visual representation; generate a context-enhanced visual representation based on the basic visual representation; map the context-enhanced visual representation to a hash vector;

[0040] S103: Perform binarization processing on the hash vector to obtain a hash representation of the image to be processed.

[0041] As one or more embodiments, the image to be processed is extracted to extract the basic visual representation; based on the basic visual representation, the context-enhanced visual representation is generated; the context-enhanced visual representation is mapped to a hash vector; the trained image Encoder to ...

Embodiment 2

[0100] This embodiment provides a weakly supervised deep context-aware image representation system;

[0101] A weakly supervised deep context-aware image representation system, including:

[0102] An acquisition module configured to: acquire an image to be processed;

[0103] A representation extraction module configured to: perform representation extraction on the image to be processed to extract a basic visual representation; generate a context-enhanced visual representation based on the basic visual representation; map the context-enhanced visual representation to a hash vector;

[0104] The binarization processing module is configured to: perform binarization processing on the hash vector to obtain a hash representation of the image to be processed.

[0105]It should be noted here that the above acquisition module, representation extraction module and binarization processing module correspond to steps S101 to S103 in Embodiment 1, and the examples and application scenario...

Embodiment 3

[0109] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.

[0110] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, o...

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 a weakly-supervised depth context-aware image representation method and system. The method comprises the steps of obtaining a to-be-processed image; performing representation extraction on the to-be-processed image, and extracting basic visual representation; generating a context-enhanced visual representation based on the basic visual representation; mapping the context-enhanced visual representation into a hash vector; and performing binarization processing on the hash vector to obtain hash representation of the to-be-processed image. According to the method, the semantic information of the image is fully captured, and the discrimination of image representation is enhanced in a unified framework. Distinguishing loss is introduced, and image representation is forced to regenerate a label. In this way, the discrimination of image representation can be enhanced, and the quality of hash codes is further improved; compared with the prior art, the method has the advantage that the image retrieval performance based on hash representation is improved.

Description

technical field [0001] The present application relates to the technical field of image representation, in particular to a weakly supervised deep context-aware image representation method and system. Background technique [0002] The statements in this section merely mention the background art related to this application, and do not necessarily constitute the prior art. [0003] With the popularity of social networks and mobile smartphones, a large number of pictures are recorded and shared by netizens. In order to overcome the storage cost brought by massive images and meet the needs of efficient image retrieval, image hash representation learning has attracted more and more research interest. Inspired by the success of deep neural networks in representation learning, research focus has shifted to exploring deep image hashing representation learning methods. Although they have achieved satisfactory progress, most of the works are supervised learning methods. In other word...

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): G06F16/583G06F16/55G06K9/62G06N3/04
Inventor 刘萌田传发周迪齐孟津聂秀山
Owner SHANDONG JIANZHU 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