TY - GEN
T1 - Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response
AU - Alam, Firoj
AU - Ofli, Ferda
AU - Imran, Muhammad
AU - Alam, Tanvirul
AU - Qazi, Umair
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12/7
Y1 - 2020/12/7
N2 - 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.
AB - 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.
KW - Benchmarking
KW - Crisis computing
KW - Deep learning
KW - Disaster Image Classification
KW - Natural disasters
KW - Social media
UR - http://www.scopus.com/inward/record.url?scp=85103687176&partnerID=8YFLogxK
U2 - 10.1109/ASONAM49781.2020.9381294
DO - 10.1109/ASONAM49781.2020.9381294
M3 - Conference contribution
AN - SCOPUS:85103687176
T3 - Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020
SP - 151
EP - 158
BT - Proceedings of the 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020
A2 - Atzmuller, Martin
A2 - Coscia, Michele
A2 - Missaoui, Rokia
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020
Y2 - 7 December 2020 through 10 December 2020
ER -