GPU-Friendly Neural Networks for Remote Sensing Scene Classification
- 2 September 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X), 1-5
- https://doi.org/10.1109/lgrs.2020.3019378
Abstract
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.Keywords
Funding Information
- Junta de Extremadura (GR18060, PID2019-105660RB-C21, TIN2016-76635-C2-1-R (AEI/ERDF, UE), gaZ: T58_17R)
This publication has 25 references indexed in Scilit:
- AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2017
- Remote Sensing Image Scene Classification: Benchmark and State of the ArtProceedings of the IEEE, 2017
- Training Deep Convolutional Neural Networks for Land–Cover Classification of High-Resolution ImageryIEEE Geoscience and Remote Sensing Letters, 2017
- Cloud implementation of the K-means algorithm for hyperspectral image analysisThe Journal of Supercomputing, 2016
- Convolutional Neural Network Based Automatic Object Detection on Aerial ImagesIEEE Geoscience and Remote Sensing Letters, 2016
- Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing ImageryRemote Sensing, 2015
- Scene Classification via a Gradient Boosting Random Convolutional Network FrameworkIEEE Transactions on Geoscience and Remote Sensing, 2015
- Deep Learning Based Feature Selection for Remote Sensing Scene ClassificationIEEE Geoscience and Remote Sensing Letters, 2015
- Bag-of-visual-words and spatial extensions for land-use classificationPublished by Association for Computing Machinery (ACM) ,2010
- Remote sensing for exploration; an overviewEconomic Geology, 1983