% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Zhang:890969,
author = {Zhang, Run and Cavallaro, Gabriele and Jitsev, Jenia},
title = {{S}uper-{R}esolution of {L}arge {V}olumes of {S}entinel-2
{I}mages with {H}igh {P}erformance {D}istributed {D}eep
{L}earning},
reportid = {FZJ-2021-01285},
pages = {617 - 620},
year = {2020},
abstract = {This work proposes a novel distributed deep learning
modelfor Remote Sensing (RS) images super-resolution. High
PerformanceComputing (HPC) systems with GPUs are used
toaccelerate the learning of the unknown low to high
resolutionmapping from large volumes of Sentinel-2 data. The
proposeddeep learning model is based on self-attention
mechanismand residual learning. The results demonstrate that
stateof-the-art performance can be achieved by keeping the
size ofthe model relatively small. Synchronous data
parallelism isapplied to scale up the training process
without severe performanceloss. Distributed training is thus
shown to speed uplearning substantially while keeping
performance intact.},
month = {Sep},
date = {2020-09-26},
organization = {2020 IEEE International Geoscience and
Remote Sensing Symposium, Online event
(Hawaii), 26 Sep 2020 - 2 Oct 2020},
cin = {JSC},
ddc = {610},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {512 - Data-Intensive Science and Federated Computing
(POF3-512) / HBP - The Human Brain Project (604102)},
pid = {G:(DE-HGF)POF3-512 / G:(EU-Grant)604102},
typ = {PUB:(DE-HGF)8},
UT = {WOS:000664335300139},
doi = {10.1109/IGARSS39084.2020.9323734},
url = {https://juser.fz-juelich.de/record/890969},
}