CrisisViT: A Robust Vision Transformer for Crisis Image Classification

Zijun Long, Richard McCreadie, Muhammad Imran

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

2 Citations (Scopus)

Abstract

In times of emergency, crisis response agencies need to quickly and accurately assess the situation on the ground in order to deploy relevant services and resources. However, authorities often have to make decisions based on limited information, as data on affected regions can be scarce until local response services can provide first-hand reports. Fortunately, the widespread availability of smartphones with high-quality cameras has made citizen journalism through social media a valuable source of information for crisis responders. However, analyzing the large volume of images posted by citizens requires more time and effort than is typically available. To address this issue, this paper proposes the use of state-of-the-art deep neural models for automatic image classification/tagging, specifically by adapting transformer-based architectures for crisis image classification (CrisisViT). We leverage the new Incidents1M crisis image dataset to develop a range of new transformer-based image classification models. Through experimentation over the standard Crisis image benchmark dataset, we demonstrate that the CrisisViT models significantly outperform previous approaches in emergency type, image relevance, humanitarian category, and damage severity classification. Additionally, we show that the new Incidents1M dataset can further augment the CrisisViT models resulting in an additional 1.25% absolute accuracy gain.

Original languageEnglish
Title of host publicationProceedings - 20th Global Information Systems for Crisis Response and Management Conference, ISCRAM 2023
PublisherInformation Systems for Crisis Response and Management, ISCRAM
Pages309-319
Number of pages11
ISBN (Electronic)9798218217495
Publication statusPublished - 2023
Event20th Global Information Systems for Crisis Response and Management Conference, ISCRAM 2023 - Omaha, United States
Duration: 28 May 202331 May 2023

Publication series

NameProceedings of the International ISCRAM Conference
Volume2023-text
ISSN (Electronic)2411-3387

Conference

Conference20th Global Information Systems for Crisis Response and Management Conference, ISCRAM 2023
Country/TerritoryUnited States
CityOmaha
Period28/05/2331/05/23

Keywords

  • Crisis Management
  • Deep Learning
  • Social Media Classification
  • Supervised Learning
  • Vision transformers

Fingerprint

Dive into the research topics of 'CrisisViT: A Robust Vision Transformer for Crisis Image Classification'. Together they form a unique fingerprint.

Cite this