Variational and Deep Learning Methods in Computer Vision

Tesis Doctoral leída en la Universidad Rey Juan Carlos de Madrid en 2019. Directores de la Tesis: Juan José Pantrigo Fernández y Emanuele Schiavi

Detalhes bibliográficos
Autor: Ramírez Díaz, Iván
Formato: tesis doctoral
Fecha de publicación:2019
País:España
Recursos:Universidad Rey Juan Carlos
Repositorio:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
OAI Identifier:oai:burjcdigital.urjc.es:10115/16336
Acesso em linha:http://hdl.handle.net/10115/16336
Access Level:acceso abierto
Palavra-chave:Informática
1203.17 Informática
1203.04 Inteligencia Artificial
id ES_5aec5afc8d314d20c06d72096304ec7e
oai_identifier_str oai:burjcdigital.urjc.es:10115/16336
network_acronym_str ES
network_name_str España
repository_id_str
spelling Variational and Deep Learning Methods in Computer VisionRamírez Díaz, IvánInformática1203.17 Informática1203.04 Inteligencia ArtificialTesis Doctoral leída en la Universidad Rey Juan Carlos de Madrid en 2019. Directores de la Tesis: Juan José Pantrigo Fernández y Emanuele SchiaviComputer Vision is a field that aims to simulate the human visual system. In the last decade, with the continuous emergence of multimedia data and applications, there has been an increasing interest to exploit all this available information, which mainly consists in images and videos. Classic approaches to Computer Vision problems constitute a Bag of Tricks that have been useful for many years. With the irruption of Deep Learning, most of these techniques, all of a sudden, became old. The reasons are the impressive outperforming results of Deep Learning techniques that, taking advantage of the available data, provide an end to end solution that is nowadays easy to use, even for non experts users. Surprisingly, some Variational Methods, which can be considered as classical methods in Computer Vision, survived and maintained the state of the art leading in some specific tasks: Medical Imaging Registration for instance. The impact of Deep Learning applications in society is undeniable. Moreover, the profit of automatizing many processes and tedious tasks that are still nowadays realized by humans, should be taken as good news, since it would provide more free time for people... and thus, more time to live. The dark side of such automatization will rely on how this new techniques, framed in the Artificial Intelligence field, are democratized across society. This is, how useful in practice are those new emerging tools and who has access to them. Autonomous driving, Medical Imaging, earthquakes and pollution predictions are few examples of critical application fields where being inaccurate implies disastrous consequences. In such scenarios, classic approaches in Computer Vision, provides less uncertainty in outcomes. In this sense, classical methods are more robust, in particular Variational Methods which have a deep and strong mathematical foundations. Moreover, recently, adversarial attacks on Neural Networks have shown how easy is to fool Deep Learning systems, increasing skepticism for potential Deep Learning users as Medical experts. In this thesis we address Computer Vision problems in real scenarios from two perspectives with the usage of: (1) Variational Methods and (2) Deep Learning techniques. The former is a powerful tool that gives an extraordinary control over the expected outcomes with very accurate results if some hyperparameterization is carried out properly. However, this required (usually manual) hyper-parameterization constitutes a huge shortcoming in practice, and a limitation for a wide use by non experts. The later relies mainly on data and solves, until a certain point, an high dimensional interpolation problem with astonishing results that, however, are sometimes unpredictable (and thus dangerous) when unseen data from different distribution is tested (extrapolation).Universidad Rey Juan Carlos201920192019info:eu-repo/semantics/doctoralThesisapplication/pdfapplication/pdfhttp://hdl.handle.net/10115/16336reponame:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlosinstname:Universidad Rey Juan CarlosInglésAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:burjcdigital.urjc.es:10115/163362026-06-24T12:48:17Z
dc.title.none.fl_str_mv Variational and Deep Learning Methods in Computer Vision
title Variational and Deep Learning Methods in Computer Vision
spellingShingle Variational and Deep Learning Methods in Computer Vision
Ramírez Díaz, Iván
Informática
1203.17 Informática
1203.04 Inteligencia Artificial
title_short Variational and Deep Learning Methods in Computer Vision
title_full Variational and Deep Learning Methods in Computer Vision
title_fullStr Variational and Deep Learning Methods in Computer Vision
title_full_unstemmed Variational and Deep Learning Methods in Computer Vision
title_sort Variational and Deep Learning Methods in Computer Vision
dc.creator.none.fl_str_mv Ramírez Díaz, Iván
author Ramírez Díaz, Iván
author_facet Ramírez Díaz, Iván
author_role author
dc.subject.none.fl_str_mv Informática
1203.17 Informática
1203.04 Inteligencia Artificial
topic Informática
1203.17 Informática
1203.04 Inteligencia Artificial
description Tesis Doctoral leída en la Universidad Rey Juan Carlos de Madrid en 2019. Directores de la Tesis: Juan José Pantrigo Fernández y Emanuele Schiavi
publishDate 2019
dc.date.none.fl_str_mv 2019
2019
2019
dc.type.none.fl_str_mv info:eu-repo/semantics/doctoralThesis
format doctoralThesis
dc.identifier.none.fl_str_mv http://hdl.handle.net/10115/16336
url http://hdl.handle.net/10115/16336
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Universidad Rey Juan Carlos
publisher.none.fl_str_mv Universidad Rey Juan Carlos
dc.source.none.fl_str_mv reponame:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
instname:Universidad Rey Juan Carlos
instname_str Universidad Rey Juan Carlos
reponame_str BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
collection BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408756309164033
score 15,811543

Registos relacionados