A Novel Disaster Image Dataset and Characteristics Analysis using Attention Model

TL;DR

This paper introduces a new challenging disaster image dataset with 13,720 annotated images across multiple disaster types and damage classes, and demonstrates the effectiveness of a three-layer attention model achieving high accuracy in disaster classification.

Contribution

The paper presents a novel, diverse disaster image dataset with manual annotations and bounding boxes, along with a three-layer attention model that achieves over 95% accuracy in disaster classification.

Findings

Achieved 95.88% average five-fold validation accuracy.

On unseen test images, accuracy reached 96.48%.

Generated attention maps reveal model characteristics.

Abstract

The advancement of deep learning technology has enabled us to develop systems that outperform any other classification technique. However, success of any empirical system depends on the quality and diversity of the data available to train the proposed system. In this research, we have carefully accumulated a relatively challenging dataset that contains images collected from various sources for three different disasters: fire, water and land. Besides this, we have also collected images for various damaged infrastructure due to natural or man made calamities and damaged human due to war or accidents. We have also accumulated image data for a class named non-damage that contains images with no such disaster or sign of damage in them. There are 13,720 manually annotated images in this dataset, each image is annotated by three individuals. We are also providing discriminating image class information annotated manually with bounding box for a set of 200 test images. Images are collected from different news portals, social media, and standard datasets made available by other researchers. A three layer attention model (TLAM) is trained and average five fold validation accuracy of 95.88% is achieved. Moreover, on the 200 unseen test images this accuracy is 96.48%. We also generate and compare attention maps for these test images to determine the characteristics of the trained attention model. Our dataset is available at https://niloy193.github.io/Disaster-Dataset