Show simple item record

dc.contributor.authorParés Pont, Ferran
dc.contributor.authorGarcia Gasulla, Dario
dc.contributor.authorServat, Harald
dc.contributor.authorLabarta Mancho, Jesús José
dc.contributor.authorAyguadé Parra, Eduard
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2020-07-16T10:46:42Z
dc.date.available2020-07-16T10:46:42Z
dc.date.issued2019-11-20
dc.identifier.citationParés, F. [et al.]. "MetH: A family of high-resolution and variable-shape image challenges". 2019.
dc.identifier.otherhttps://arxiv.org/abs/1911.08953
dc.identifier.urihttp://hdl.handle.net/2117/193028
dc.description.abstractHigh-resolution and variable-shape images have not yet been properly addressed by the AI community. The approach of down-sampling data often used with convolutional neural networks is sub-optimal for many tasks, and has too many drawbacks to be considered a sustainable alternative. In sight of the increasing importance of problems that can benefit from exploiting high-resolution (HR) and variable-shape, and with the goal of promoting research in that direction, we introduce a new family of datasets (MetH). The four proposed problems include two image classification, one image regression and one super resolution task. Each of these datasets contains thousands of art pieces captured by HR and variable-shape images, labeled by experts at the Metropolitan Museum of Art. We perform an analysis, which shows how the proposed tasks go well beyond current public alternatives in both pixel size and aspect ratio variance. At the same time, the performance obtained by popular architectures on these tasks shows that there is ample room for improvement. To wrap up the relevance of the contribution we review the fields, both in AI and high-performance computing, that could benefit from the proposed challenges.
dc.description.sponsorshipThis work is partially supported by the Intel-BSC Exascale Lab agreement, by the Spanish Government through Programa Severo Ochoa (SEV-2015-0493), by the Spanish Ministry of Science and Technology through TIN2015-65316-P project, and by the Generalitat de Catalunya (contracts 2017-SGR-1414).
dc.format.extent8 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subject.lcshPattern recognition systems
dc.subject.lcshComputer vision
dc.titleMetH: A family of high-resolution and variable-shape image challenges
dc.typeExternal research report
dc.subject.lemacReconeixement de formes (Informàtica)
dc.subject.lemacVisió per ordinador
dc.contributor.groupUniversitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions
dc.rights.accessOpen Access
local.identifier.drac28894829
dc.description.versionPreprint
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/1PE/TIN2015-65316-P
dc.relation.projectidinfo:eu-repo/grantAgreement/AGAUR/2017 SGR 1414
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/1PE/SEV-2015-0493
local.citation.authorParés, F.; Garcia-Gasulla, D.; Servat, H.; Labarta, J.; Ayguadé, E.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder