MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification

Abstract

Recent research in disaster informatics demonstrates a practical and important use case of artificial intelligence to save human lives and suffering during natural disasters based on social media contents (text and images). While notable progress has been made using texts, research on exploiting the images remains relatively under-explored. To advance image-based approaches, we propose MEDIC (Available at: https://crisisnlp.qcri.org/medic/index.html), which is the largest social media image classification dataset for humanitarian response consisting of 71,198 images to address four different tasks in a multi-task learning setup. This is the first dataset of its kind: social media images, disaster response, and multi-task learning research. An important property of this dataset is its high potential to facilitate research on multi-task learning, which recently receives much interest from the machine learning community and has shown remarkable results in terms of memory, inference speed, performance, and generalization capability. Therefore, the proposed dataset is an important resource for advancing image-based disaster management and multi-task machine learning research. We experiment with different deep learning architectures and report promising results, which are above the majority baselines for all tasks. Along with the dataset, we also release all relevant scripts (https://github.com/firojalam/medic).

Multi-task Learning, Social media images, Image Classification, Natural disasters, Crisis Informatics, Deep learning, Dataset

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• How transferable are features in deep neural networks?
• An Overview of Multi-Task Learning in Deep Neural Networks
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• Multi-Task Learning with Deep Neural Networks: A Survey
• Learning Task Grouping and Overlap in Multi-task Learning
• Multi-task learning for natural language processing in the 2020s: where are we going?
• Rapid Damage Assessment Using Social Media Images by Combining Human and Machine Intelligence

Cited by in corpus (2)

• A social context-aware graph-based multimodal attentive learning framework for disaster content classification during emergencies: a benchmark dataset and method
• DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition