Cargando…

A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment

The problem of deep learning network image classification when a large number of image samples are obtained in life and with only a small amount of knowledge annotation, is preliminarily solved in this paper. First, a support vector machine expert labeling system is constructed by using a bag-of-wor...

Descripción completa

Detalles Bibliográficos
Autores principales: Kong, Yunchen, Ma, Xue, Wen, Chenglin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8839952/
https://www.ncbi.nlm.nih.gov/pubmed/35161644
http://dx.doi.org/10.3390/s22030898
_version_ 1784650497990328320
author Kong, Yunchen
Ma, Xue
Wen, Chenglin
author_facet Kong, Yunchen
Ma, Xue
Wen, Chenglin
author_sort Kong, Yunchen
collection PubMed
description The problem of deep learning network image classification when a large number of image samples are obtained in life and with only a small amount of knowledge annotation, is preliminarily solved in this paper. First, a support vector machine expert labeling system is constructed by using a bag-of-words model to extract image features from a small number of labeled samples. The labels of a large number of unlabeled image samples are automatically annotated by using the constructed SVM expert labeling system. Second, a small number of labeled samples and automatically labeled image samples are combined to form an augmented training set. A deep convolutional neural network model is created by using an augmented training set. Knowledge transfer from SVMs trained with a small number of image samples annotated by artificial knowledge to deep neural network classifiers is implemented in this paper. The problem of overfitting in neural network training with small samples is solved. Finally, the public dataset caltech256 is used for experimental verification and mechanism analysis of the performance of the new method.
format Online
Article
Text
id pubmed-8839952
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88399522022-02-13 A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment Kong, Yunchen Ma, Xue Wen, Chenglin Sensors (Basel) Article The problem of deep learning network image classification when a large number of image samples are obtained in life and with only a small amount of knowledge annotation, is preliminarily solved in this paper. First, a support vector machine expert labeling system is constructed by using a bag-of-words model to extract image features from a small number of labeled samples. The labels of a large number of unlabeled image samples are automatically annotated by using the constructed SVM expert labeling system. Second, a small number of labeled samples and automatically labeled image samples are combined to form an augmented training set. A deep convolutional neural network model is created by using an augmented training set. Knowledge transfer from SVMs trained with a small number of image samples annotated by artificial knowledge to deep neural network classifiers is implemented in this paper. The problem of overfitting in neural network training with small samples is solved. Finally, the public dataset caltech256 is used for experimental verification and mechanism analysis of the performance of the new method. MDPI 2022-01-25 /pmc/articles/PMC8839952/ /pubmed/35161644 http://dx.doi.org/10.3390/s22030898 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kong, Yunchen
Ma, Xue
Wen, Chenglin
A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment
title A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment
title_full A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment
title_fullStr A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment
title_full_unstemmed A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment
title_short A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment
title_sort new method of deep convolutional neural network image classification based on knowledge transfer in small label sample environment
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8839952/
https://www.ncbi.nlm.nih.gov/pubmed/35161644
http://dx.doi.org/10.3390/s22030898
work_keys_str_mv AT kongyunchen anewmethodofdeepconvolutionalneuralnetworkimageclassificationbasedonknowledgetransferinsmalllabelsampleenvironment
AT maxue anewmethodofdeepconvolutionalneuralnetworkimageclassificationbasedonknowledgetransferinsmalllabelsampleenvironment
AT wenchenglin anewmethodofdeepconvolutionalneuralnetworkimageclassificationbasedonknowledgetransferinsmalllabelsampleenvironment
AT kongyunchen newmethodofdeepconvolutionalneuralnetworkimageclassificationbasedonknowledgetransferinsmalllabelsampleenvironment
AT maxue newmethodofdeepconvolutionalneuralnetworkimageclassificationbasedonknowledgetransferinsmalllabelsampleenvironment
AT wenchenglin newmethodofdeepconvolutionalneuralnetworkimageclassificationbasedonknowledgetransferinsmalllabelsampleenvironment