Paper published on a website (Scientific congresses and symposiums)
How does explicit orientation encoding affect image classification of ConvNets?
Hammoudeh, Ahmad Tayseer Ahmad; Dupont, Stéphane
2022CVPR 2022 workshop: Neurovision
Peer reviewed
 

Files


Full Text
2_CameraReady_CVPR22_NeurovisionWS_Rotational_encoding.pdf
Author preprint (920.86 kB)
Request a copy

All documents in ORBi UMONS are protected by a user license.

Send to



Details



Keywords :
Artificial intelligence; convolutional neural networks; neuroscience; geometric deep learning
Abstract :
[en] Some shapes look different to us if rotated. That is attributed to the use of a rotation frame of coordinates in the human visual system. However, no evidence that ConvNets, which is a machine learning architecture, use a frame of coordinates for rotation. We investigated the effect of adding one to ConvNets. An explicit orientation encoding kernel was developed using a mathematically inspired self-supervised approach. The experimental results showed that rotation encoding improved the accuracy of classifying rotated images and the resilience against noise. The orientation encoding kernel was embedded in a layer named (ConvOrient) that will be open-sourced.
Disciplines :
Computer science
Neurosciences & behavior
Electrical & electronics engineering
Author, co-author :
Hammoudeh, Ahmad Tayseer Ahmad ;  Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Dupont, Stéphane  ;  Université de Mons - UMONS > Faculté des Sciences > Service d'Intelligence Artificielle
Language :
English
Title :
How does explicit orientation encoding affect image classification of ConvNets?
Publication date :
19 June 2022
Event name :
CVPR 2022 workshop: Neurovision
Event date :
6/2022
Peer reviewed :
Peer reviewed
Research unit :
S841 - MAIA - Service d'Intelligence Artificielle
F105 - Information, Signal et Intelligence artificielle
Research institute :
R450 - Institut NUMEDIART pour les Technologies des Arts Numériques
Funders :
Service Public de Wallonie Recherche
Funding number :
2010235
Funding text :
This work was supported by Service Public de Wallonie Recherche under grant n° 2010235 ARIAC by DIGITAL-WALLONIA4.AI
Available on ORBi UMONS :
since 04 July 2022

Statistics


Number of views
62 (14 by UMONS)
Number of downloads
23 (2 by UMONS)

Bibliography


Similar publications



Contact ORBi UMONS