Supercharge Your Innovation With Domain-Expert AI Agents!

Small sample image classification method based on multi-head feature cooperation

A classification method and small sample technology, applied in the field of pattern recognition, can solve the problem of not fully mining the value of unlabeled samples.

Active Publication Date: 2021-09-10
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the value of unlabeled samples is not fully exploited in the testing phase

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
  • Small sample image classification method based on multi-head feature cooperation
  • Small sample image classification method based on multi-head feature cooperation
  • Small sample image classification method based on multi-head feature cooperation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0060] The following will be combined with figure 1 , a small-sample image classification method based on multi-head feature collaboration in an embodiment of the present invention will be described in detail.

[0061] Reference attached figure 1 As shown, a small sample image classification method based on multi-head feature cooperation in the embodiment of the present invention includes:

[0062] Step 110: Extract image features using convolutional neural network.

[0063] The convolutional neural network model Resnet-12 model is used to extract image features. Specifically, first, the image scale size is changed to 84x84, and then the Resnet-12 model is called to obtain the features of the image to be processed. Among them, the ...

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 small sample image classification method based on multi-head feature cooperation, which belongs to the technical field of pattern recognition, uses embedded features extracted by a plurality of feature extractors at the same time, introduces a subspace learning method, and converts original multi-head features into a unified low-dimensional representation space, thereby being beneficial to reducing redundant information, and effectively solving the problem that different embedded features are located in different feature spaces, and measurement scales are inconsistent. Besides, the combined weight of each multi-head feature is automatically updated by designing a weight calculation part, and the processed multi-head embedded features are cascaded to obtain cooperative representation of samples, so that the problem of reasonable use of the multi-head features is effectively solved.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a small-sample image classification method based on multi-head feature collaboration. Background technique [0002] Inspired by human cognitive learning, scholars have proposed a small-sample image classification problem. After learning a large number of samples in a limited category, using prior knowledge, when encountering a new category, only a small amount of sample data can be quickly and accurately Learn. In recent years, problems related to small sample learning have become a new important research direction in the field of machine learning, and are considered to be one of the development directions of the next generation of artificial intelligence. [0003] At present, the main small-sample image classification methods are as follows: [0004] (1) Small-sample image classification method based on data expansion: The small-sample image classification method b...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/285G06F18/2411G06F18/25G06F18/214
Inventor 刘宝弟兴雷邵帅刘伟锋王延江
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com