Semi-supervised image classification method based on random region interpolation

A classification method, a semi-supervised technique, applied in the field of computer vision, which can solve problems such as areas that are not necessarily important or unnecessary

Active Publication Date: 2021-02-19
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]The purpose of the present invention is to overcome the problem that existing deep neural networks always tend to learn the most discrimina

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 image classification method based on random region interpolation
  • Semi-supervised image classification method based on random region interpolation
  • Semi-supervised image classification method based on random region interpolation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with specific examples.

[0043] Such as figure 1 As shown, the semi-supervised image classification method based on random area interpolation provided in this embodiment includes the following steps:

[0044] S1. Divide the training data into a set of real label images No ground truth label image collection and the test data set details as follows:

[0045] First, flip the image horizontally with a probability of 0.5, then fill the width and height of the image with 2 pixels, then randomly crop the image into 32x32 pixels, then subtract the average value of the image pixels, and finally go through whitening processing; as needed To classify the image data, first divide the image data into training data and test data sets Two categories; then the training data is divided into two categories: the real label image set and the set of untrue labeled images The ratio of 1:50, that is, the train...

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 image classification method based on random region interpolation, and the method comprises the steps: selecting a small number of images with real labels froma training set, and taking other remaining images as images without real labels; simultaneously sending the two types of images to a random region interpolation module; wherein the interpolation process is different, the image with the real label can directly generate a new augmented image through interpolation, but each image without the real label cannot be normally interpolated, so that high-confidence label information can be obtained through a teacher network to serve as a temporary label of each image without the real label, and then interpolation operation is carried out; and trainingthe network by using the new augmented image until the network model is trained to a preset number of times. Random region interpolation is carried out on two types of images at the same time, a new augmented image is generated for training a classification network, and the generalization performance of a training model is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a semi-supervised image classification method based on random area interpolation. Background technique [0002] With the growth of social media and web services, tons of photos are uploaded every day. Labeling them manually for model training becomes less feasible. However, in a growing number of applications having ground truth labeled data is insufficient and unlabeled data is readily available. In order to solve the problem of learning in part of the data with real labels, semi-supervised learning is studied to effectively reduce the dependence on the data with real labels by using the data without real labels. [0003] Semi-supervised learning is a key issue in the field of pattern recognition and machine learning, and it is also a learning method that combines supervised learning and unsupervised learning. Semi-supervised learning uses a large amount of unlabeled ...

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
CPCG06N3/08G06N3/088G06N3/045G06F18/241G06F18/214
Inventor 曾祥平霍晓阳吴斯
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap