Show simple item record

dc.contributor.authorMoya Sánchez, Eduardo Ulises
dc.contributor.authorXambó Descamps, Sebastián
dc.contributor.authorSalazar Colores, Sebastián
dc.contributor.authorSánchez-Pérez, Abraham
dc.contributor.authorCortés García, Claudio Ulises
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Matemàtiques
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2021-07-20T08:29:29Z
dc.date.issued2021
dc.identifier.citationMoya, E. [et al.]. A quaternion deterministic monogenic CNN layer for contrast invariance. A: "Systems, patterns and data engineering with geometric calculi". Berlín: Springer, 2021, p. 133-152.
dc.identifier.isbn978-3-030-74486-1
dc.identifier.urihttp://hdl.handle.net/2117/349717
dc.description.abstractDeep learning (DL) is attracting considerable interest as it currently achieves remarkable performance in many branches of science and technology. However, current DL cannot guarantee capabilities of the mammalian visual systems such as lighting changes. This paper proposes a deterministic entry layer capable of classifying images even with low-contrast conditions. We achieve this through an improved version of the quaternion monogenic wavelets. We have simulated the atmospheric degradation of the CIFAR-10 and the Dogs and Cats datasets to generate realistic contrast degradations of the images. The most important result is that the accuracy gained by using our layer is substantially more robust to illumination changes than nets without such a layer.
dc.description.sponsorshipThe authors would like to thank to CONACYT and Barcelona supercomputing Center. Sebastián Salazar-Colores (CVU 477758) would like to thank CONACYT (Consejo Nacional de Ciencia y Tecnología) for the financial support of his PhD studies under Scholarship 285651. Ulises Moya and Ulises Cortés are member of the Sistema Nacional de Investigadores CONACyT.
dc.format.extent20 p.
dc.language.isoeng
dc.publisherSpringer
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject.lcshMachine learning
dc.subject.lcshImage analysis
dc.subject.lcshNeural networks (Computer science)
dc.titleA quaternion deterministic monogenic CNN layer for contrast invariance
dc.typePart of book or chapter of book
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacImatges -- Anàlisi
dc.subject.lemacXarxes neuronals (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic
dc.identifier.doi10.1007/978-3-030-74486-1_7
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://link.springer.com/book/10.1007/978-3-030-74486-1
dc.rights.accessRestricted access - publisher's policy
local.identifier.drac31940748
dc.description.versionPostprint (author's final draft)
dc.date.lift2022-07-17
local.citation.authorMoya, E.; Xambó, S.; Salazar-Colores, S.; Sánchez-Pérez, A.; Cortés, U.
local.citation.pubplaceBerlín
local.citation.publicationNameSystems, patterns and data engineering with geometric calculi
local.citation.startingPage133
local.citation.endingPage152


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