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

Towards Out-of-Distribution Detection for Remote Sensing

Gawlikowski, Jakob and Saha, Sudipan and Kruspe, Anna and Zhu, Xiao Xiang (2021) Towards Out-of-Distribution Detection for Remote Sensing. In: International Geoscience and Remote Sensing Symposium (IGARSS), pp. 8676-8679. IGARSS 2021, 11.-16.7.2021, Brüssel, Belgien. doi: 10.1109/IGARSS47720.2021.9553266.

[img] PDF - Only accessible within DLR bis July 2022

Official URL: https://ieeexplore.ieee.org/document/9553266


In remote sensing, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data, differences in the geographic area, and multi-sensor differences. Deep learning based models may behave in unexpected manners when subjected to test data that has such distributional shifts from the training data, also called out-of-distribution (OOD) examples. Vulnerability to OOD data severely reduces the reliability of deep learning based models. In this work, we address this issue by proposing a model to quantify distributional uncertainty of deep learning based remote sensing models. In particular, we adopt a Dirichlet Prior Network for remote sensing data. The approach seeks to maximize the representation gap between the in-domain and OOD examples for a better identification of unknown examples at test time. Experimental results on three exemplary test scenarios show that the proposed model can detect OOD images in remote sensing.

Item URL in elib:https://elib.dlr.de/145041/
Document Type:Conference or Workshop Item (Speech)
Title:Towards Out-of-Distribution Detection for Remote Sensing
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Gawlikowski, Jakobjakob.gawlikowski (at) dlr.deUNSPECIFIED
Zhu, Xiao Xiangxiaoxiang.zhu (at) dlr.deUNSPECIFIED
Date:July 2021
Journal or Publication Title:International Geoscience and Remote Sensing Symposium (IGARSS)
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
DOI :10.1109/IGARSS47720.2021.9553266
Page Range:pp. 8676-8679
Keywords:Out-of- distribution, open set recognition, robustness, remote sensing
Event Title:IGARSS 2021
Event Location:Brüssel, Belgien
Event Type:international Conference
Event Dates:11.-16.7.2021
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Artificial Intelligence
Location: Jena , Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Institute of Data Science > Datamangagement and Analysis
Deposited By: Gawlikowski, Jakob
Deposited On:01 Nov 2021 08:32
Last Modified:02 Nov 2021 11:46

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.