Cargando…
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...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8622369/ https://www.ncbi.nlm.nih.gov/pubmed/34833805 http://dx.doi.org/10.3390/s21227731 |
_version_ | 1784605677564461056 |
---|---|
author | Pintelas, Emmanuel Livieris, Ioannis E. Pintelas, Panagiotis E. |
author_facet | Pintelas, Emmanuel Livieris, Ioannis E. Pintelas, Panagiotis E. |
author_sort | Pintelas, Emmanuel |
collection | PubMed |
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 | Online Article Text |
id | pubmed-8622369 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-86223692021-11-27 A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets Pintelas, Emmanuel Livieris, Ioannis E. Pintelas, Panagiotis E. Sensors (Basel) Article 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. MDPI 2021-11-20 /pmc/articles/PMC8622369/ /pubmed/34833805 http://dx.doi.org/10.3390/s21227731 Text en © 2021 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 Pintelas, Emmanuel Livieris, Ioannis E. Pintelas, Panagiotis E. A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets |
title | 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_short | 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 |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8622369/ https://www.ncbi.nlm.nih.gov/pubmed/34833805 http://dx.doi.org/10.3390/s21227731 |
work_keys_str_mv | AT pintelasemmanuel aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT livierisioannise aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT pintelaspanagiotise aconvolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT pintelasemmanuel convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT livierisioannise convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets AT pintelaspanagiotise convolutionalautoencodertopologyforclassificationinhighdimensionalnoisyimagedatasets |