DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Deep Learning Earth Observation Classification Using ImageNet Pre-trained Networks

Marmanis, Dimitrios and Datcu, Mihai and Esch, Thomas and Stilla, Uwe (2016) Deep Learning Earth Observation Classification Using ImageNet Pre-trained Networks. IEEE Geoscience and Remote Sensing Letters, 13 (1), pp. 105-109. IEEE - Institute of Electrical and Electronics Engineers. DOI: 10.1109/LGRS.2015.2499239 ISSN 1545-598X

[img] PDF

Official URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7342907


Deep learning methods such as convolutional neural networks (CNNs) can deliver highly accurate classification results when provided with large enough data sets and respective labels. However, using CNNs along with limited labeled data can be problematic, as this leads to extensive overfitting. In this letter, we propose a novel method by considering a pretrained CNN designed for tackling an entirely different classification problem, namely, the ImageNet challenge, and exploit it to extract an initial set of representations. The derived representations are then transferred into a supervised CNN classifier, along with their class labels, effectively training the system. Through this two-stage framework, we successfully deal with the limited-data problem in an end-to-end processing scheme. Comparative results over the UC Merced Land Use benchmark prove that our method significantly outperforms the previously best stated results, improving the overall accuracy from 83.1% up to 92.4%. Apart from statistical improvements, our method introduces a novel feature fusion algorithm that effectively tackles the large data dimensionality by using a simple and computationally efficient approach.

Item URL in elib:https://elib.dlr.de/99809/
Document Type:Article
Title:Deep Learning Earth Observation Classification Using ImageNet Pre-trained Networks
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Marmanis, DimitriosDimitrios.Marmanis (at) dlr.deUNSPECIFIED
Datcu, Mihaimihai.datcu (at) dlr.deUNSPECIFIED
Esch, ThomasThomas.Esch (at) dlr.deUNSPECIFIED
Stilla, Uwestilla (at) tum.deUNSPECIFIED
Date:January 2016
Journal or Publication Title:IEEE Geoscience and Remote Sensing Letters
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
DOI :10.1109/LGRS.2015.2499239
Page Range:pp. 105-109
Frery, Alejandroacfrery@gmail.com
Publisher:IEEE - Institute of Electrical and Electronics Engineers
Keywords:deep learning, classification, pre-trained networks
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben Fernerkundung der Landoberfläche (old)
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Land Surface
Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Adam, Fathalrahman
Deposited On:02 Dec 2015 12:40
Last Modified:31 Jul 2019 19:56

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.