Cargando…

Orthogonal Local Image Descriptors with Convolutional Autoencoders

This work proposes the use of deep learning architectures, and in particular Convolutional Autencoders (CAE’s), to incorporate an explicit component of orthogonality to the computation of local image descriptors. For this purpose we present a methodology based on the computation of dot products amon...

Descripción completa

Detalles Bibliográficos
Autores principales: Roman-Rangel, Edgar, Marchand-Maillet, Stephane
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7297571/
http://dx.doi.org/10.1007/978-3-030-49076-8_15
_version_ 1783547033859129344
author Roman-Rangel, Edgar
Marchand-Maillet, Stephane
author_facet Roman-Rangel, Edgar
Marchand-Maillet, Stephane
author_sort Roman-Rangel, Edgar
collection PubMed
description This work proposes the use of deep learning architectures, and in particular Convolutional Autencoders (CAE’s), to incorporate an explicit component of orthogonality to the computation of local image descriptors. For this purpose we present a methodology based on the computation of dot products among the hidden outputs of the center-most layer of a convolutional autoencoder. This is, the dot product between the responses of the different kernels of the central layer (sections of a latent representation). We compare this dot product against an indicator of orthogonality, which in the presence of non-orthogonal hidden representations, back-propagates a gradient through the network, adjusting its parameters to produce new representations which will be closer to have orthogonality among them in future iterations. Our results show that the proposed methodology is suitable for the estimation of local image descriptors that are orthogonal to one another, which is often a desirable feature in many patter recognition tasks.
format Online
Article
Text
id pubmed-7297571
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-72975712020-06-17 Orthogonal Local Image Descriptors with Convolutional Autoencoders Roman-Rangel, Edgar Marchand-Maillet, Stephane Pattern Recognition Article This work proposes the use of deep learning architectures, and in particular Convolutional Autencoders (CAE’s), to incorporate an explicit component of orthogonality to the computation of local image descriptors. For this purpose we present a methodology based on the computation of dot products among the hidden outputs of the center-most layer of a convolutional autoencoder. This is, the dot product between the responses of the different kernels of the central layer (sections of a latent representation). We compare this dot product against an indicator of orthogonality, which in the presence of non-orthogonal hidden representations, back-propagates a gradient through the network, adjusting its parameters to produce new representations which will be closer to have orthogonality among them in future iterations. Our results show that the proposed methodology is suitable for the estimation of local image descriptors that are orthogonal to one another, which is often a desirable feature in many patter recognition tasks. 2020-04-29 /pmc/articles/PMC7297571/ http://dx.doi.org/10.1007/978-3-030-49076-8_15 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Roman-Rangel, Edgar
Marchand-Maillet, Stephane
Orthogonal Local Image Descriptors with Convolutional Autoencoders
title Orthogonal Local Image Descriptors with Convolutional Autoencoders
title_full Orthogonal Local Image Descriptors with Convolutional Autoencoders
title_fullStr Orthogonal Local Image Descriptors with Convolutional Autoencoders
title_full_unstemmed Orthogonal Local Image Descriptors with Convolutional Autoencoders
title_short Orthogonal Local Image Descriptors with Convolutional Autoencoders
title_sort orthogonal local image descriptors with convolutional autoencoders
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7297571/
http://dx.doi.org/10.1007/978-3-030-49076-8_15
work_keys_str_mv AT romanrangeledgar orthogonallocalimagedescriptorswithconvolutionalautoencoders
AT marchandmailletstephane orthogonallocalimagedescriptorswithconvolutionalautoencoders