A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets

Deep convolutional neural networks have shown remarkable performance in the image classification domain. However, Deep Learning models are vulnerable to noise and redundant information encapsulated into the high-dimensional raw input images, leading to unstable and unreliable predictions. Autoencode...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Emmanuel Pintelas, Ioannis E. Livieris, Panagiotis E. Pintelas
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	convolutional autoencoders dimensionality reduction deep learning convolutional neural networks computer vision image classification Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/5dd1ec8af35a4523a22dd4d2f89657f0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5dd1ec8af35a4523a22dd4d2f89657f0
record_format	dspace
spelling	oai:doaj.org-article:5dd1ec8af35a4523a22dd4d2f89657f02021-11-25T18:58:50ZA Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets10.3390/s212277311424-8220https://doaj.org/article/5dd1ec8af35a4523a22dd4d2f89657f02021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7731https://doaj.org/toc/1424-8220Deep convolutional neural networks have shown remarkable performance in the image classification domain. However, Deep Learning models are vulnerable to noise and redundant information encapsulated into the high-dimensional raw input images, leading to unstable and unreliable predictions. Autoencoders constitute an unsupervised dimensionality reduction technique, proven to filter out noise and redundant information and create robust and stable feature representations. In this work, in order to resolve the problem of DL models’ vulnerability, we propose a convolutional autoencoder topological model for compressing and filtering out noise and redundant information from initial high dimensionality input images and then feeding this compressed output into convolutional neural networks. Our results reveal the efficiency of the proposed approach, leading to a significant performance improvement compared to Deep Learning models trained with the initial raw images.Emmanuel PintelasIoannis E. LivierisPanagiotis E. PintelasMDPI AGarticleconvolutional autoencodersdimensionality reductiondeep learningconvolutional neural networkscomputer visionimage classificationChemical technologyTP1-1185ENSensors, Vol 21, Iss 7731, p 7731 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	convolutional autoencoders dimensionality reduction deep learning convolutional neural networks computer vision image classification Chemical technology TP1-1185
spellingShingle	convolutional autoencoders dimensionality reduction deep learning convolutional neural networks computer vision image classification Chemical technology TP1-1185 Emmanuel Pintelas Ioannis E. Livieris Panagiotis E. Pintelas A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets
description	Deep convolutional neural networks have shown remarkable performance in the image classification domain. However, Deep Learning models are vulnerable to noise and redundant information encapsulated into the high-dimensional raw input images, leading to unstable and unreliable predictions. Autoencoders constitute an unsupervised dimensionality reduction technique, proven to filter out noise and redundant information and create robust and stable feature representations. In this work, in order to resolve the problem of DL models’ vulnerability, we propose a convolutional autoencoder topological model for compressing and filtering out noise and redundant information from initial high dimensionality input images and then feeding this compressed output into convolutional neural networks. Our results reveal the efficiency of the proposed approach, leading to a significant performance improvement compared to Deep Learning models trained with the initial raw images.
format	article
author	Emmanuel Pintelas Ioannis E. Livieris Panagiotis E. Pintelas
author_facet	Emmanuel Pintelas Ioannis E. Livieris Panagiotis E. Pintelas
author_sort	Emmanuel Pintelas
title	A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets
title_short	A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets
title_full	A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets
title_fullStr	A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets
title_full_unstemmed	A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets
title_sort	convolutional autoencoder topology for classification in high-dimensional noisy image datasets
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/5dd1ec8af35a4523a22dd4d2f89657f0
work_keys_str_mv	AT emmanuelpintelas aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT ioanniselivieris aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT panagiotisepintelas aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT emmanuelpintelas convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT ioanniselivieris convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT panagiotisepintelas convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets
_version_	1718410464843530240

A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets

Ejemplares similares