Mostra el registre d'ítem simple
A quaternion deterministic monogenic CNN layer for contrast invariance
dc.contributor.author | Moya Sánchez, Eduardo Ulises |
dc.contributor.author | Xambó Descamps, Sebastián |
dc.contributor.author | Salazar Colores, Sebastián |
dc.contributor.author | Sánchez-Pérez, Abraham |
dc.contributor.author | Cortés García, Claudio Ulises |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Matemàtiques |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.contributor.other | Barcelona Supercomputing Center |
dc.date.accessioned | 2021-07-20T08:29:29Z |
dc.date.available | 2022-07-17T00:26:10Z |
dc.date.issued | 2021 |
dc.identifier.citation | Moya, 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.isbn | 978-3-030-74486-1 |
dc.identifier.uri | http://hdl.handle.net/2117/349717 |
dc.description.abstract | Deep 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.sponsorship | The 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.extent | 20 p. |
dc.language.iso | eng |
dc.publisher | Springer |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic |
dc.subject.lcsh | Machine learning |
dc.subject.lcsh | Image analysis |
dc.subject.lcsh | Neural networks (Computer science) |
dc.title | A quaternion deterministic monogenic CNN layer for contrast invariance |
dc.type | Part of book or chapter of book |
dc.subject.lemac | Aprenentatge automàtic |
dc.subject.lemac | Imatges -- Anàlisi |
dc.subject.lemac | Xarxes neuronals (Informàtica) |
dc.contributor.group | Universitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic |
dc.identifier.doi | 10.1007/978-3-030-74486-1_7 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://link.springer.com/book/10.1007/978-3-030-74486-1 |
dc.rights.access | Open Access |
local.identifier.drac | 31940748 |
dc.description.version | Postprint (author's final draft) |
local.citation.author | Moya, E.; Xambó, S.; Salazar-Colores, S.; Sánchez-Pérez, A.; Cortés, U. |
local.citation.pubplace | Berlín |
local.citation.publicationName | Systems, patterns and data engineering with geometric calculi |
local.citation.startingPage | 133 |
local.citation.endingPage | 152 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Capítols de llibre [200]
-
Capítols de llibre [15]
-
Capítols de llibre [22]
-
Capítols de llibre [86]