3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts

3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts

Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than ot...

Full description

Bibliographic Details
Main Authors: Ibon Merino, Jon Azpiazu, Anthony Remazeilles, Basilio Sierra
Format: Article
Language:English
Published: MDPI AG 2021-02-01
Series:Sensors
Subjects:
computer vision
deep learning
transfer learning
object recognition
Online Access:https://www.mdpi.com/1424-8220/21/4/1078

Internet

https://www.mdpi.com/1424-8220/21/4/1078

Similar Items