Abstract
Labeled data scarcity at the time of an ongoing disaster has encouraged the researchers to use the labeled data from some previous disaster for training and transferring the knowledge to the current disaster task using Domain Adaptation (DA). However, often labeled data from more than one previous disaster may be available. As all deep learning models are data-hungry and perform better if fed with more annotated data, it is advisable to use data from multiple sources for training a Deep Convolutional Neural Network (DCNN). One of the easiest ways is to simply combine the data from multiple sources and use it for training. However, this arrangement is not that straightforward. The models trained on the combined data from various sources do not perform well on the target, mainly due to distribution discrepancies between multiple sources. This has motivated us to explore the challenging area of multi-source domain adaptation for disaster management. The aim is to learn the domain invariant features and representations across the domains and transfer more related knowledge to solve the target task with improved accuracy than single-source or combined-source domain adaptation. This study proposes a Multi-Source Domain Adaptation framework for Disaster Management (MSDA-DM) to classify disaster images posted on social media based on unsupervised DA with adversarial training. The empirical results obtained confirm that the proposed model MSDA-DM performs better than single-source DA by up to 10.83% and combined-source DA by up to 5.06% in terms of F1-score for different sets of source and target disaster domains. We also compare our model with current state-of-the-art models. The main challenge of multi-source DA is the choice of the relevant sources taken for training since, unlike single-source DA that handles only source-target distribution drift, the multi-source DA network has to address both source-target and source-source distribution drifts.