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...
Main Authors: | Ibon Merino, Jon Azpiazu, Anthony Remazeilles, Basilio Sierra |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/4/1078 |
Similar Items
-
Histogram-Based Descriptor Subset Selection for Visual Recognition of Industrial Parts
by: Ibon Merino, et al.
Published: (2020-05-01) -
Ensemble Pretrained Convolutional Neural Networks for the Classification of Insulator Surface Conditions
by: Arailym Serikbay, et al.
Published: (2024-11-01) -
Convolutional Neural Network for Satellite Imagery
by: Vladimir Khryashchev, et al.
Published: (2018-05-01) -
Understanding convolutional neural networks
by: Fong, R
Published: (2020) -
Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks
by: Joao Paulo Schwarz Schuler, et al.
Published: (2022-06-01)