%0 Conference Paper
%A Zhang, Run
%A Cavallaro, Gabriele
%A Jitsev, Jenia
%T Super-Resolution of Large Volumes of Sentinel-2 Images with High Performance Distributed Deep Learning
%M FZJ-2021-01285
%P 617 - 620
%D 2020
%X 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.
%B 2020 IEEE International Geoscience and Remote Sensing Symposium
%C 26 Sep 2020 - 2 Oct 2020, Online event (Hawaii)
Y2 26 Sep 2020 - 2 Oct 2020
M2 Online event, Hawaii
%F PUB:(DE-HGF)8
%9 Contribution to a conference proceedings
%U <Go to ISI:>//WOS:000664335300139
%R 10.1109/IGARSS39084.2020.9323734
%U https://juser.fz-juelich.de/record/890969