000119879 001__ 119879
000119879 005__ 20240319081014.0
000119879 0247_ $$2doi$$a10.1109/LGRS.2020.3019378
000119879 0248_ $$2sideral$$a130535
000119879 037__ $$aART-2022-130535
000119879 041__ $$aeng
000119879 100__ $$aHaut, Juan M.
000119879 245__ $$aGPU-friendly neural networks for remote sensing scene classification
000119879 260__ $$c2022
000119879 5060_ $$aAccess copy available to the general public$$fUnrestricted
000119879 5203_ $$aConvolutional 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.
000119879 536__ $$9info:eu-repo/grantAgreement/ES/AEI-FEDER/PID2019-105660RB-C21$$9info:eu-repo/grantAgreement/ES/DGA/T58-17R$$9info:eu-repo/grantAgreement/ES/MINECO/TIN2016-76635-C2-1-R
000119879 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000119879 590__ $$a4.8$$b2022
000119879 592__ $$a1.284$$b2022
000119879 591__ $$aGEOCHEMISTRY & GEOPHYSICS$$b10 / 87 = 0.115$$c2022$$dQ1$$eT1
000119879 593__ $$aGeotechnical Engineering and Engineering Geology$$c2022$$dQ1
000119879 591__ $$aIMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY$$b9 / 28 = 0.321$$c2022$$dQ2$$eT1
000119879 593__ $$aElectrical and Electronic Engineering$$c2022$$dQ1
000119879 591__ $$aREMOTE SENSING$$b14 / 34 = 0.412$$c2022$$dQ2$$eT2
000119879 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b74 / 274 = 0.27$$c2022$$dQ2$$eT1
000119879 594__ $$a6.4$$b2022
000119879 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000119879 700__ $$0(orcid)0000-0002-7057-4283$$aAlcolea, Adrian$$uUniversidad de Zaragoza
000119879 700__ $$aPaoletti, Mercedes E.
000119879 700__ $$aPlaza, Javier
000119879 700__ $$0(orcid)0000-0002-7532-2720$$aResano, Javier$$uUniversidad de Zaragoza
000119879 700__ $$aPlaza, Antonio
000119879 7102_ $$15007$$2035$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Arquit.Tecnología Comput.
000119879 773__ $$g19 (2022), 8001005 [5 pp.]$$pIEEE Geoscience and Remote Sensing Letters$$tIEEE Geoscience and Remote Sensing Letters$$x1545-598X
000119879 8564_ $$s556286$$uhttps://zaguan.unizar.es/record/119879/files/texto_completo.pdf$$yPostprint
000119879 8564_ $$s3465957$$uhttps://zaguan.unizar.es/record/119879/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000119879 909CO $$ooai:zaguan.unizar.es:119879$$particulos$$pdriver
000119879 951__ $$a2024-03-18-15:26:08
000119879 980__ $$aARTICLE