119879 20240319081014.0 doi 10.1109/LGRS.2020.3019378 sideral 130535 ART-2022-130535 eng Haut, Juan M. GPU-friendly neural networks for remote sensing scene classification 2022 Access copy available to the general public Unrestricted Convolutional neural networks (CNNs) have proven to be very efficient for the analysis of remote sensing (RS) images. Due to the inherent complexity of extracting features from these images, along with the increasing amount of data to be processed (and the diversity of applications), there is a clear tendency to develop and employ increasingly deep and complex CNNs. In this regard, graphics processing units (GPUs) are frequently used to optimize their execution, both for the training and inference stages, optimizing the performance of neural models through their many-core architecture. Hence, the efficient use of the GPU resources should be at the core of optimizations. This letter analyzes the possibilities of using a new family of CNNs, denoted as TResNets, to provide an efficient solution to the RS scene classification problem. Moreover, the considered models have been combined with mixed precision to enhance their training performance. Our experimental results, conducted over three publicly available RS data sets, show that the proposed networks achieve better accuracy and more efficient use of GPU resources than other state-of-the-art networks. Source code is available at https://github.com/mhaut/GPUfriendlyRS. info:eu-repo/grantAgreement/ES/AEI-FEDER/PID2019-105660RB-C21 info:eu-repo/grantAgreement/ES/DGA/T58-17R info:eu-repo/grantAgreement/ES/MINECO/TIN2016-76635-C2-1-R info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 4.8 2022 GEOCHEMISTRY & GEOPHYSICS 10 / 87 = 0.115 2022 Q1 T1 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY 9 / 28 = 0.321 2022 Q2 T1 REMOTE SENSING 14 / 34 = 0.412 2022 Q2 T2 ENGINEERING, ELECTRICAL & ELECTRONIC 74 / 274 = 0.27 2022 Q2 T1 1.284 2022 Geotechnical Engineering and Engineering Geology 2022 Q1 Electrical and Electronic Engineering 2022 Q1 6.4 2022 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Alcolea, Adrian Universidad de Zaragoza (orcid)0000-0002-7057-4283 Paoletti, Mercedes E. Plaza, Javier Resano, Javier Universidad de Zaragoza (orcid)0000-0002-7532-2720 Plaza, Antonio 5007 035 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Arquit.Tecnología Comput. 19 (2022), 8001005 [5 pp.] IEEE Geoscience and Remote Sensing Letters IEEE Geoscience and Remote Sensing Letters 1545-598X 556286 http://zaguan.unizar.es/record/119879/files/texto_completo.pdf Postprint 3465957 http://zaguan.unizar.es/record/119879/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:119879 articulos driver 2024-03-18-15:26:08 ARTICLE