kCV-B: BOOTSTRAP WITH CROSS-VALIDATION FOR DEEP LEARNING MODEL DEVELOPMENT, ASSESSMENT AND SELECTION
Yazarlar (6)
A. Nurunnabi
University of Luxembourg, Lüksemburg
University of Luxembourg, Lüksemburg
F. N. Teferle
University of Luxembourg, Lüksemburg
University of Luxembourg, Lüksemburg
D. F. Laefer
Nyu Tandon School of Engineering, Amerika Birleşik Devletleri
Nyu Tandon School of Engineering, Amerika Birleşik Devletleri
F. Remondino Bruno Kessler Foundation, İtalya
Prof. Dr. İsmail Rakıp KARAŞ Karabük Üniversitesi, Türkiye
J. Li
University of Waterloo, Kanada
University of Waterloo, Kanada
| Bildiri Türü |
Tebliğ/Bildiri
|
Bildiri Dili | İngilizce |
| Bildiri Alt Türü | Tam Metin Olarak Yayınlanan Tebliğ (Uluslararası Kongre/Sempozyum) | ||
| Bildiri Niteliği | |||
| DOI Numarası | 10.5194/isprs-archives-XLVIII-4-W3-2022-111-2022 | ||
| Kongre Adı | International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences ISPRS Archives | ||
| Kongre Tarihi | / | ||
| Basıldığı Ülke | Basıldığı Şehir | ||
| Bildiri Linki | https://publons.com/wos-op/publon/55175338/ | ||
| UAK Araştırma Alanları |
Mühendislik
|
||
| Özet |
| 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 (eg, 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. |
| Anahtar Kelimeler |
| Classification | Cross-Validation | Neural Network | PointNet | Semantic Segmentation | Supervised Machine Learning |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Scopus | 4 |
| Google Scholar | 6 |