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

A multi-graph regularized deep matrix factorization method for multi-view clustering

A matrix decomposition, multi-view technology, applied in the field of image processing, can solve problems such as insufficient accuracy, inability to preserve the manifold structure of each view, and no consideration, to achieve the effect of improving accuracy, eliminating adverse effects, and effectively and rationally optimizing

Active Publication Date: 2021-09-28
JIANGSU UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention provides a multi-graph regularized depth matrix decomposition method for multi-view clustering, which effectively solves the problem that the multi-view clustering (MAC) method in the prior art does not consider and cannot preserve the manifold of each view. structure, leading to technical problems with insufficient accuracy of multi-view clustering (MAC) methods

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
  • A multi-graph regularized deep matrix factorization method for multi-view clustering
  • A multi-graph regularized deep matrix factorization method for multi-view clustering
  • A multi-graph regularized deep matrix factorization method for multi-view clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to more clearly describe the embodiments of the present invention or the technical solutions in the prior art, the specific embodiments of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative efforts, and obtain other implementations.

[0039] For the semi-nonnegative matrix (Deep Semi-NMF) decomposition, the objective function is where X∈IR m×n Represents the input data of n samples, each sample is an m-dimensional feature, A ∈ IR m×r , W ∈ IR r×n , W≥0, where W represents the “soft” clustering assignment matrix. While in reality, natural data may contain different pattern connections (or factors), for example, expressing the effect of lighting on a face dataset, a single non-negative matrix...

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 present invention provides a multi-graph regularization depth matrix decomposition method oriented to multi-view clustering, comprising: obtaining the multi-view sample set X={X (1) ,...,X (υ) ,...,X (V)}, where V represents the number of views, k υ is the dimension of the view sample, n is the number of multi-view samples; construct an objective function according to the multi-view sample set: according to the objective function, use an iterative weighted method to output the feature matrix D m , to complete the decomposition of the multi-view sample set X. It uses multi-graph regularization items to maintain the inherent geometric structure information in the coefficient matrix of each layer, so as to ensure that the coefficient matrix of each layer is optimized effectively and reasonably, so as to improve the accuracy of multi-view clustering.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a multi-image regularization depth matrix decomposition method for multi-view clustering. Background technique [0002] Since many real data are composed of different representations or views, multi-view clustering (MAC) has recently received increasing attention. The key to multi-view clustering is to explore complementary information so that the clustering problem can be solved. The previous method to solve this problem is usually to find low-dimensional representations in high-dimensional data, so as to improve computational efficiency. [0003] Traditional clustering aims to identify groups of "similar behaviors" in a single view of data. Since real-world data is always obtained from multiple sources or represented by several different feature sets, multi-view clustering (MAC) is intensively studied by exploiting heterogeneous data to achieve the same goal experime...

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): G06K9/62
CPCG06F18/23213
Inventor 舒振球陆翼孙艳武张杰汤嘉立李仁璞范洪辉叶飞跃
Owner JIANGSU 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