Unpublished conference/Abstract (Scientific congresses and symposiums)
Improving the Training of Deep Convolutional Neural Networks for Art Classification: from Transfer Learning to Multi-Task Learning
Sabatelli, Matthia; Kestemont, Mike; Geurts, Pierre
2019The 6th Digital Humanities (DH) Benelux Conference
 

Files


Full Text
Matthia_Sabatelli_Improving_Training_of_DCNNs_DHBenelux2019.pdf
Publisher postprint (337.06 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Deep Convolutional Neural Networks; Transfer Learning; Multi-Task Learning
Abstract :
[en] Deep Convolutional Neural Networks have become the most popular algorithm for Computer Vision (CV) problems. However, they are well known to be particularly hard to train. A large set of possible hyperparameters, combined with the need for large amounts of training data, can put serious constraints on their optimization procedure. In this paper, we explore several strategies which can facilitate their training when classifying images representing heritage objects, a CV area which is relatively unexplored.
Disciplines :
Computer science
Author, co-author :
Sabatelli, Matthia ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
Kestemont, Mike;  Universiteit Antwerpen, Belgium > Antwerp Center for Digital Humanities and Literary Criticism (ACDC)
Geurts, Pierre ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
Language :
English
Title :
Improving the Training of Deep Convolutional Neural Networks for Art Classification: from Transfer Learning to Multi-Task Learning
Publication date :
October 2019
Event name :
The 6th Digital Humanities (DH) Benelux Conference
Event date :
11-13 septembre 2019
Audience :
International
Available on ORBi :
since 14 October 2019

Statistics


Number of views
79 (10 by ULiège)
Number of downloads
68 (6 by ULiège)

Bibliography


Similar publications



Contact ORBi