Geometric Transformations Embedded into Convolutional Neural Networks

dc.contributor.authorTarasiuk, Paweł
dc.contributor.authorPryczek, Michał
dc.date.accessioned2021-07-15T06:54:26Z
dc.date.available2021-07-15T06:54:26Z
dc.date.issued2016
dc.description.abstractThis paper presents a novel extension to convolutional neural networks. While CNNs are known for invariance to object translation, changes to the other parameters could make the image recognition tasks diffcult – that includes rotations and scaling. Some improvement in this area could be achieved with embedded geometric transformations used inside the CNNs. In order to provide a practical solution, which allows fast propagation and learning of the modified networks, “fast geometric transformations” are introduced.en_EN
dc.identifier.citationTarasiuk, P., & Pryczek, M. (2016). Geometric Transformations Embedded into Convolutional Neural Networks. Journal of Applied Computer Science, 24(3), 33-48. https://doi.org/10.34658/jacs.2016.24.3.33-48
dc.identifier.doihttps://doi.org/10.34658/jacs.2016.24.3.33-48
dc.identifier.doi10.34658/jacs.2016.24.3.33-48
dc.identifier.issn1507-0360
dc.identifier.urihttp://hdl.handle.net/11652/3850
dc.identifier.urihttps://doi.org/10.34658/jacs.2016.24.3.33-48
dc.language.isoenen_EN
dc.page.numbers. 33-48
dc.publisherWydawnictwo Politechniki Łódzkiejpl_PL
dc.publisherLodz University of Technology Pressen_EN
dc.relation.ispartofJournal of Applied Computer Science, Vol. 24, No. 3, Wydawnictwo Politechniki Łódzkiej, Łódź 2016, ISSN 1507-0360.
dc.rightsFair use conditionen_EN
dc.rightsDla wszystkich w zakresie dozwolonego użytkupl_PL
dc.rights.licenseLUT Licenseen_EN
dc.rights.licenseLicencja PŁpl_PL
dc.subjectartificial intelligenceen_EN
dc.subjectmachine learningen_EN
dc.subjectdeep learningen_EN
dc.subjectconvolutional neural networksen_EN
dc.subjectimage processingen_EN
dc.subjectimage recognitionen_EN
dc.subjectgeometric transformationsen_EN
dc.subjectsztuczna inteligencjapl_PL
dc.subjectnauczanie maszynowepl_PL
dc.subjectgłęboka naukapl_PL
dc.subjectsplotowe sieci neuronowepl_PL
dc.subjectprzetwarzanie obrazupl_PL
dc.subjectrozpoznawanie obrazupl_PL
dc.subjectprzekształcenia geometrycznepl_PL
dc.titleGeometric Transformations Embedded into Convolutional Neural Networksen_EN
dc.typeArtykułpl_PL
dc.typeArticleen_EN

Pliki

Oryginalne pliki
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
3_Geom_trans_Tarasiuk_Pryczek_2016.pdf
Rozmiar:
400.53 KB
Format:
Adobe Portable Document Format
Opis:
Licencja
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
license.txt
Rozmiar:
1.71 KB
Format:
Item-specific license agreed upon to submission
Opis: