TY  - CONF
AU  - Aach, Marcel
AU  - Sedona, Rocco
AU  - Lintermann, Andreas
AU  - Cavallaro, Gabriele
AU  - Neukirchen, Helmut
AU  - Riedel, Morris
TI  - Accelerating Hyperparameter Tuning of a Deep Learning Model for Remote Sensing Image Classification
PB  - IEEE
M1  - FZJ-2022-03638
SP  - 263-266
PY  - 2022
AB  - Deep Learning models have proven necessary in dealing with the challenges posed by the continuous growth of data volume acquired from satellites and the increasing complexity of new Remote Sensing applications. To obtain the best performance from such models, it is necessary to fine-tune their hyperparameters. Since the models might have massive amounts of parameters that need to be tuned, this process requires many computational resources. In this work, a method to accelerate hyperparameter optimization on a High-Performance Computing system is proposed. The data batch size is increased during the training, leading to a more efficient execution on Graphics Processing Units. The experimental results confirm that this method reduces the runtime of the hyperparameter optimization step by a factor of 3 while achieving the same validation accuracy as a standard training procedure with a fixed batch size.
T2  - 2022 IEEE International Geoscience and Remote Sensing Symposium
CY  - 17 Jul 2022 - 22 Jul 2022, Kuala Lumpur (Malaysia)
Y2  - 17 Jul 2022 - 22 Jul 2022
M2  - Kuala Lumpur, Malaysia
LB  - PUB:(DE-HGF)8
UR  - <Go to ISI:>//WOS:000920916600066
DO  - DOI:10.1109/IGARSS46834.2022.9883257
UR  - https://juser.fz-juelich.de/record/910149
ER  -