% 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{Sedona:893825,
      author       = {Sedona, Rocco and Cavallaro, Gabriele and Riedel, Morris
                      and Book, Matthias},
      title        = {{E}nhancing {L}arge {B}atch {S}ize {T}raining of {D}eep
                      {M}odels for {R}emote {S}ensing {A}pplications},
      publisher    = {IEEE},
      reportid     = {FZJ-2021-02864},
      pages        = {1583-1586},
      year         = {2021},
      comment      = {2021 IEEE International Geoscience and Remote Sensing
                      Symposium IGARSS : [Proceedings] - IEEE, 2021. - ISBN
                      978-1-6654-0369-6 - doi:10.1109/IGARSS47720.2021.9555136},
      booktitle     = {2021 IEEE International Geoscience and
                       Remote Sensing Symposium IGARSS :
                       [Proceedings] - IEEE, 2021. - ISBN
                       978-1-6654-0369-6 -
                       doi:10.1109/IGARSS47720.2021.9555136},
      abstract     = {A 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.},
      month         = {Jul},
      date          = {2021-07-12},
      organization  = {IEEE International Geoscience and
                       Remote Sensing Symposium, Brussels
                       (Belgium), 12 Jul 2021 - 16 Jul 2021},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511)},
      pid          = {G:(DE-HGF)POF4-5112},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      UT           = {WOS:001250139801213},
      doi          = {10.1109/IGARSS47720.2021.9555136},
      url          = {https://juser.fz-juelich.de/record/893825},
}