Mostrar el registro sencillo del ítem
Improving the reliability of deep learning computational ghost imaging with prediction uncertainty based on neighborhood feature maps
dc.contributor.author | Kataoka, Shoma | |
dc.contributor.author | Mizutani, Yasuhiro | |
dc.contributor.author | Ipus, Erick | |
dc.contributor.author | Nitta, Kouichi | |
dc.contributor.author | Matoba, Osamu | |
dc.contributor.author | Takaya, Yasuhiro | |
dc.contributor.author | Tajahuerce, Enrique | |
dc.date.accessioned | 2024-06-20T06:59:04Z | |
dc.date.available | 2024-06-20T06:59:04Z | |
dc.date.issued | 2024-05-10 | |
dc.identifier.citation | Shoma Kataoka, Yasuhiro Mizutani, Tsutomu Uenohara, Erick Ipus, Koichi Nitta, Osamu Matoba, Yasuhiro Takaya, and Enrique Tajahuerce, "Improving the reliability of deep learning computational ghost imaging with prediction uncertainty based on neighborhood feature maps," Appl. Opt. 63, 3736-3744 (2024) | ca_CA |
dc.identifier.issn | 1559-128X | |
dc.identifier.issn | 2155-3165 | |
dc.identifier.uri | http://hdl.handle.net/10234/207862 | |
dc.description.abstract | Defect inspection is required in various fields, and many researchers have attempted deep-learning algorithms for inspections. Deep-learning algorithms have advantages in terms of accuracy and measurement time; however, the reliability of deep-learning outputs is problematic in precision measurements. This study demonstrates that iterative estimation using neighboring feature maps can evaluate the uncertainty of the outputs and shows that unconfident error predictions have higher uncertainties. In ghost imaging using deep learning, the experimental results show that removing outputs with higher uncertainties improves the accuracy by approximately 15.7%. | ca_CA |
dc.format.extent | 9 p. | ca_CA |
dc.language.iso | eng | ca_CA |
dc.publisher | Optica Publishing Group | ca_CA |
dc.relation | Caracterización y control espaciotemporal de haces de luz y su aplicación a las ciencias de la vida | ca_CA |
dc.relation.isPartOf | Applied Optics, 2024, vol. 63, no 14 | ca_CA |
dc.rights | © Optica Publishing Group | ca_CA |
dc.rights.uri | http://rightsstatements.org/vocab/CNE/1.0/ | ca_CA |
dc.subject | deep learning | ca_CA |
dc.subject | iterative estimation | ca_CA |
dc.subject | neighboring feature maps | ca_CA |
dc.title | Improving the reliability of deep learning computational ghost imaging with prediction uncertainty based on neighborhood feature maps | ca_CA |
dc.type | info:eu-repo/semantics/article | ca_CA |
dc.identifier.doi | https://doi.org/10.1364/AO.511817 | |
dc.rights.accessRights | info:eu-repo/semantics/restrictedAccess | ca_CA |
dc.relation.publisherVersion | https://opg.optica.org/ao/fulltext.cfm?uri=ao-63-14-3736&id=549566 | ca_CA |
dc.description.sponsorship | Japan Society for the Promotion of Science (JP19H02154, JP20H05886, JP22H01499, JP23KJ1439, JPJSBP120229927); Ministerio de Ciencia e Innovación (PID2022-142907OB-I00/AEI/10.13039/501100011033); Generalitat Valenciana (Prometeo/2020/029). | |
dc.description.sponsorship | This work was supported by JSPS KAKENHI. E. Tajahuerce acknowledges grant PID2022-142907OB-I00, funded by MCIN/AEI/10.13039/501100011033 and by “ERDF: A Way of Making Europe,” and grant Prometeo/2020/029, funded by Generalitat Valenciana. | |
dc.type.version | info:eu-repo/semantics/publishedVersion | ca_CA |
project.funder.identifier | http://dx.doi.org/10.13039/501100011033 | ca_CA |
project.funder.name | Japan Society for the Promotion of Science | ca_CA |
project.funder.name | Ministerio de Ciencia e Innovación | ca_CA |
project.funder.name | Generalitat Valenciana | ca_CA |
oaire.awardNumber | JP19H02154 | ca_CA |
oaire.awardNumber | JP20H05886 | ca_CA |
oaire.awardNumber | JP22H01499 | ca_CA |
oaire.awardNumber | JP23KJ1439 | ca_CA |
oaire.awardNumber | JPJSBP120229927 | ca_CA |
oaire.awardNumber | MCIN/PEICTI2021-2023/PID2022-142907OB-I00 | ca_CA |
oaire.awardNumber | Prometeo/2020/029 | ca_CA |
Ficheros en el ítem
Ficheros | Tamaño | Formato | Ver |
---|---|---|---|
No hay ficheros asociados a este ítem. |
Este ítem aparece en la(s) siguiente(s) colección(ones)
-
INIT_Articles [751]