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

Semi-supervised multi-mark distance metric learning method fusing local metric

A technology of distance measurement and learning method, which is applied in the field of multi-label learning scenarios, can solve the problem of less feature space processing, reduce the cost of human labeling, and promote the effect of practical application

Pending Publication Date: 2019-11-05
SOUTHEAST UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, multi-label learning algorithms mainly consider the correlation between labels from the label space, and do less processing of the feature space.

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
  • Semi-supervised multi-mark distance metric learning method fusing local metric
  • Semi-supervised multi-mark distance metric learning method fusing local metric
  • Semi-supervised multi-mark distance metric learning method fusing local metric

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0037] Such as figure 1 As shown in , a semi-supervised multi-label distance metric learning method that fuses local metrics includes the following steps:

[0038] 1. Sampling any multi-label application scenarios such as images, videos, texts, etc. to obtain training data, extract corresponding features and manually label a small number of examples to obtain training data D=L∪U={(x i ,Y i )|1≤i≤n}∪{x j |1≤j≤m}, where Y i Label vectors for q-dimensions.

[0039] 2. Preprocess the training data. For the labeled data L, filter out the samples whose label occupancy rate is less than the set threshold. For the unlabeled data U, remove abnormal points through clustering and other operations to improve the sample quality.

[0040] 3. Based on the characteristics of multi-label data, the distance measure to be learned is expressed as a combined distance measure...

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 semi-supervised multi-mark distance measurement learning method fusing local measurement, and the method comprises the steps: extracting training data of any multi-mark application scene, and marking a small amount of data; for labeled data, filtering out samples with the labeling occupancy smaller than a set threshold value, removing abnormal points of unlabeled data through clustering and other operations, and improving the sample quality; expressing the distance metric to be learned as a combined distance metric form; constructing an optimization item based on thedistance metric representation; constructing a multi-mark loss item and manifold regularization item joint optimization model, and learning distance measurement; mapping the original data to a distance measurement space, and then performing learning by using an existing semi-supervised multi-mark learning algorithm to obtain a semi-supervised multi-mark classifier fused with local measurement; andinputting a to-be-predicted sample into the classifier to obtain a labeled sample. By adopting the method, the manual labeling cost can be reduced, and the practical application of the multi-label learning framework is promoted.

Description

technical field [0001] The invention is applicable to any multi-label learning scene with a small amount of labeled data and a large amount of unlabeled data, and in particular relates to a semi-supervised multi-label distance metric learning method with fusion of local metrics. Background technique [0002] In recent years, multi-label learning has attracted extensive attention from researchers for its ability to model objects with rich semantic information and a large number of research results have emerged. At present, multi-label learning algorithms mainly consider the correlation between labels from the label space, and do less processing on the feature space. [0003] There are a lot of unlabeled data in practical applications, and obtaining object labels requires a lot of manpower and material resources. Based on this, semi-supervised multi-label learning is proposed. This learning scenario includes a small amount of labeled multi-label data and a large amount of unla...

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): G06K9/62
CPCG06F18/2155G06F18/23G06F18/22G06F18/24
Inventor 张敏灵孙彦苹
Owner SOUTHEAST 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