Identifying disaster damage images using a domain adaptation approach

Xukun Li, Cornelia Caragea, Doina Caragea*, Muhammad Imran, Ferda Ofli

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

45 Citations (Scopus)

Abstract

Approaches for effectively filtering useful situational awareness information posted by eyewitnesses of disasters, in real time, are greatly needed. While many studies have focused on filtering textual information, the research on filtering disaster images is more limited. In particular, there are no studies on the applicability of domain adaptation to filter images from an emergent target disaster, when no labeled data is available for the target disaster. To fill in this gap, we propose to apply a domain adaptation approach, called domain adversarial neural networks (DANN), to the task of identifying images that show damage. The DANN approach has VGG-19 as its backbone, and uses the adversarial training to find a transformation that makes the source and target data indistinguishable. Experimental results on several pairs of disasters suggest that the DANN model generally gives similar or better results as compared to the VGG-19 model fine-tuned on the source labeled data.

Original languageEnglish
Title of host publicationISCRAM 2019 - Proceedings
Subtitle of host publication16th International Conference on Information Systems for Crisis Response and Management
EditorsZeno Franco, Jose J. Gonzalez, Jose H. Canos
PublisherInformation Systems for Crisis Response and Management, ISCRAM
Pages633-645
Number of pages13
ISBN (Electronic)9788409104987
Publication statusPublished - 2019
Event16th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2019 - Valencia, Spain
Duration: 19 May 201922 May 2019

Publication series

NameProceedings of the International ISCRAM Conference
Volume2019-May
ISSN (Electronic)2411-3387

Conference

Conference16th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2019
Country/TerritorySpain
CityValencia
Period19/05/1922/05/19

Keywords

  • Disaster damage
  • Domain adaptation
  • Domain adversarial neural networks
  • Image classification

Fingerprint

Dive into the research topics of 'Identifying disaster damage images using a domain adaptation approach'. Together they form a unique fingerprint.

Cite this