000893825 001__ 893825
000893825 005__ 20250310131243.0
000893825 0247_ $$2doi$$a10.1109/IGARSS47720.2021.9555136
000893825 0247_ $$2WOS$$aWOS:001250139801213
000893825 037__ $$aFZJ-2021-02864
000893825 1001_ $$0P:(DE-Juel1)178695$$aSedona, Rocco$$b0
000893825 1112_ $$aIEEE International Geoscience and Remote Sensing Symposium$$cBrussels$$d2021-07-12 - 2021-07-16$$gIGARSS 2021$$wBelgium
000893825 245__ $$aEnhancing Large Batch Size Training of Deep Models for Remote Sensing Applications
000893825 260__ $$bIEEE$$c2021
000893825 29510 $$a2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS : [Proceedings] - IEEE, 2021. - ISBN 978-1-6654-0369-6 - doi:10.1109/IGARSS47720.2021.9555136
000893825 300__ $$a1583-1586
000893825 3367_ $$2ORCID$$aCONFERENCE_PAPER
000893825 3367_ $$033$$2EndNote$$aConference Paper
000893825 3367_ $$2BibTeX$$aINPROCEEDINGS
000893825 3367_ $$2DRIVER$$aconferenceObject
000893825 3367_ $$2DataCite$$aOutput Types/Conference Paper
000893825 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1635430213_13275
000893825 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000893825 520__ $$aA wide variety of Remote Sensing (RS) missions arecontinuously acquiring a large volume of data every day. The availability of large datasets has propelled Deep Learning (DL) methods also in the RS domain. Convolutional Neural Networks (CNNs) have become the state of the art when tackling the classification of images, however the process of training is time consuming. In this work we exploit the Layer-wise Adaptive Moments optimizer for Batch training (LAMB) optimizer to use large batch size training on High-Performance Computing (HPC) systems. With the use of LAMB combined with learning rate scheduling and warm-up strategies, the experimental results on RS data classification demonstrate that a ResNet50 can be trained faster with batch sizes up to 32K.
000893825 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000893825 588__ $$aDataset connected to CrossRef Conference
000893825 7001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b1$$eCorresponding author
000893825 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b2
000893825 7001_ $$0P:(DE-HGF)0$$aBook, Matthias$$b3
000893825 773__ $$a10.1109/IGARSS47720.2021.9555136
000893825 8564_ $$uhttps://juser.fz-juelich.de/record/893825/files/IGARSS2021_SAT6.pdf$$yRestricted
000893825 909CO $$ooai:juser.fz-juelich.de:893825$$pVDB
000893825 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178695$$aForschungszentrum Jülich$$b0$$kFZJ
000893825 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b1$$kFZJ
000893825 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b2$$kFZJ
000893825 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
000893825 9141_ $$y2021
000893825 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000893825 980__ $$acontrib
000893825 980__ $$aVDB
000893825 980__ $$acontb
000893825 980__ $$aI:(DE-Juel1)JSC-20090406
000893825 980__ $$aUNRESTRICTED