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

Out-of-Distribution Detection in Satellite Image Classification

Gawlikowski, Jakob and Saha, Sudipan and Kruspe, Anna and Zhu, Xiao Xiang (2021) Out-of-Distribution Detection in Satellite Image Classification. In: RobustML Workshop at ICLR 2021, pp. 1-5. ICRL. The Ninth International Conference on Learning Representations, 3.-7. May 2021, Virtual event.

[img] PDF
264kB

Official URL: https://sites.google.com/connect.hku.hk/robustml-2021/accepted-papers/paper-012

Abstract

In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area. Deep learning based models may behave in unexpected manner when subjected to test data that has such distributional shifts from the training data, also called out-of-distribution (OOD) examples. Predictive uncertainly analysis is an emerging research topic which has not been explored much in context of satellite image analysis. Towards this, we adopt a Dirichlet Prior Network based model to quantify distributional uncertainty of deep learning models for remote sensing. 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 the efficacy of the model in satellite image analysis.

Item URL in elib:https://elib.dlr.de/142285/
Document Type:Conference or Workshop Item (Other)
Title:Out-of-Distribution Detection in Satellite Image Classification
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Gawlikowski, JakobJakob.Gawlikowski (at) dlr.deUNSPECIFIED
Saha, SudipanTU MünchenUNSPECIFIED
Kruspe, AnnaTU MünchenUNSPECIFIED
Zhu, Xiao Xiangxiaoxiang.zhu (at) dlr.dehttps://orcid.org/0000-0001-5530-3613
Date:May 2021
Journal or Publication Title:RobustML Workshop at ICLR 2021
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 1-5
Publisher:ICRL
Status:Published
Keywords:out-of-distribution, satellite image classification
Event Title:The Ninth International Conference on Learning Representations
Event Location:Virtual event
Event Type:international Conference
Event Dates:3.-7. May 2021
Organizer:ICLR
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: Bratasanu, Ion-Dragos
Deposited On:21 May 2021 17:03
Last Modified:03 Nov 2021 09:50

Repository Staff Only: item control page

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