kCV-B: BOOTSTRAP WITH CROSS-VALIDATION FOR DEEP LEARNING MODEL DEVELOPMENT, ASSESSMENT AND SELECTION

Basit Öğe Kaydı
dc.contributor.authorNurunnabi, A.
dc.contributor.authorTeferle, F.N.
dc.contributor.authorLaefer, D.F.
dc.contributor.authorRemondino, F.
dc.contributor.authorKaras, I.R.
dc.contributor.authorLi, J.
dc.date.accessioned2024-09-29T16:16:03Z
dc.date.available2024-09-29T16:16:03Z
dc.date.issued2022
dc.departmentKarabük Üniversitesien_US
dc.description7th International Conference on Smart City Applications, SCA 2022 -- 19 October 2022 through 21 October 2022 -- Castelo Branco -- 185014en_US
dc.description.abstractThis study investigates the inability of two popular data splitting techniques: train/test split and k-fold cross-validation that are to create training and validation data sets, and to achieve sufficient generality for supervised deep learning (DL) methods. This failure is mainly caused by their limited ability of new data creation. In response, the bootstrap is a computer based statistical resampling method that has been used efficiently for estimating the distribution of a sample estimator and to assess a model without having knowledge about the population. This paper couples cross-validation and bootstrap to have their respective advantages in view of data generation strategy and to achieve better generalization of a DL model. This paper contributes by: (i) developing an algorithm for better selection of training and validation data sets, (ii) exploring the potential of bootstrap for drawing statistical inference on the necessary performance metrics (e.g., mean square error), and (iii) introducing a method that can assess and improve the efficiency of a DL model. The proposed method is applied for semantic segmentation and is demonstrated via a DL based classification algorithm, PointNet, through aerial laser scanning point cloud data. © 2022 International Society for Photogrammetry and Remote Sensing. All rights reserved.en_US
dc.description.sponsorshipG. D. of Luxembourg; Programme Fonds Européen de Developpment Régional; SOLSTICE; National Science Foundation, NSF, (1940145); European Regional Development Fund, ERDFen_US
dc.identifier.doi10.5194/isprs-archives-XLVIII-4-W3-2022-111-2022
dc.identifier.endpage118en_US
dc.identifier.issn1682-1750
dc.identifier.issue4/W3-2022en_US
dc.identifier.scopus2-s2.0-85144337686en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage111en_US
dc.identifier.urihttps://doi.org/10.5194/isprs-archives-XLVIII-4-W3-2022-111-2022
dc.identifier.urihttps://hdl.handle.net/20.500.14619/8828
dc.identifier.volume48en_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInternational Society for Photogrammetry and Remote Sensingen_US
dc.relation.ispartofInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archivesen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectClassificationen_US
dc.subjectCross-Validationen_US
dc.subjectNeural Networken_US
dc.subjectPointNeten_US
dc.subjectSemantic Segmentationen_US
dc.subjectSupervised Machine Learningen_US
dc.titlekCV-B: BOOTSTRAP WITH CROSS-VALIDATION FOR DEEP LEARNING MODEL DEVELOPMENT, ASSESSMENT AND SELECTIONen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu