Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response

Firoj Alam, Ferda Ofli, Muhammad Imran, Tanvirul Alam, Umair Qazi

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

46 Citations (Scopus)

Abstract

During a disaster event, images shared on social media helps crisis managers gain situational awareness and assess incurred damages, among other response tasks. Recent advances in computer vision and deep neural networks have enabled the development of models for real-Time image classification for a number of tasks, including detecting crisis incidents, filtering irrelevant images, classifying images into specific humanitarian categories, and assessing the severity of damage. Despite several efforts, past works mainly suffer from limited resources (i.e., labeled images) available to train more robust deep learning models. In this study, we propose new datasets for disaster type detection, and informativeness classification, and damage severity assessment. Moreover, we relabel existing publicly available datasets for new tasks. We identify exact-and near-duplicates to form non-overlapping data splits, and finally consolidate them to create larger datasets. In our extensive experiments, we benchmark several state-of-The-Art deep learning models and achieve promising results. We release our datasets and models publicly, aiming to provide proper baselines as well as to spur further research in the crisis informatics community.

Original languageEnglish
Title of host publicationProceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020
EditorsMartin Atzmuller, Michele Coscia, Rokia Missaoui
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages151-158
Number of pages8
ISBN (Electronic)9781728110561
DOIs
Publication statusPublished - 7 Dec 2020
Event12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020 - Virtual, Online, Netherlands
Duration: 7 Dec 202010 Dec 2020

Publication series

NameProceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020

Conference

Conference12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020
Country/TerritoryNetherlands
CityVirtual, Online
Period7/12/2010/12/20

Keywords

  • Benchmarking
  • Crisis computing
  • Deep learning
  • Disaster Image Classification
  • Natural disasters
  • Social media

Fingerprint

Dive into the research topics of 'Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response'. Together they form a unique fingerprint.

Cite this