Paper published in a book (Scientific congresses, symposiums and conference proceedings)
kCV-B: Bootstrap with Cross-Validation for Deep Learning Model Development, Assessment and Selection
Nurunnabi, Abdul Awal Md; Teferle, Felix Norman; Laefer, Debra et al.
2022In kCV-B: Bootstrap with Cross-Validation for Deep Learning Model Development, Assessment and Selection
Peer reviewed
 

Files


Full Text
Bootstrap and CV for Deep Learning_SCA'22_CR.pdf
Publisher postprint (2.13 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Classification; Cross-Validation; Neural Network; PointNet; Semantic Segmentation; Supervised Machine Learning
Abstract :
[en] This 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.
Research center :
ULHPC - University of Luxembourg: High Performance Computing
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Nurunnabi, Abdul Awal Md ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Teferle, Felix Norman ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Laefer, Debra;  2Center for Urban Science and Progress ; Department of Civil and Urban Engineering > New York University, USA
Remondino, Fabio;  33D Optical Metrology (3DOM) unit > Bruno Kessler Foundation (FBK), Trento, Italy
Karas, Ismail Rakip;  Department of Computer Engineering > Karabuk University, Karabuk, Turkey
Li, Jonatha;  5Geography and Environmental Management > University of Waterloo, Canada
External co-authors :
yes
Language :
English
Title :
kCV-B: Bootstrap with Cross-Validation for Deep Learning Model Development, Assessment and Selection
Publication date :
October 2022
Event name :
The 7th Smart City Applications, International Conference
Event place :
Castelo Branco, Portugal
Event date :
from 19-10-2022 to 21-10-2022
Audience :
International
Main work title :
kCV-B: Bootstrap with Cross-Validation for Deep Learning Model Development, Assessment and Selection
Publisher :
ISPRS
Peer reviewed :
Peer reviewed
Focus Area :
Computational Sciences
Name of the research project :
SOLSTICE
Available on ORBilu :
since 30 November 2022

Statistics


Number of views
97 (2 by Unilu)
Number of downloads
38 (2 by Unilu)

Scopus citations®
 
0
Scopus citations®
without self-citations
0

Bibliography


Similar publications



Contact ORBilu