BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledge
This addresses the problem of efficient damage assessment for disaster response teams, though it is incremental as it builds on existing graph and semi-supervised methods.
The paper tackles building damage change detection in disaster informatics by proposing BLDNet, a semi-supervised framework using graph convolutional networks and urban domain knowledge, achieving improved performance on the xBD dataset and the 2020 Beirut Port Explosion data.
Change detection is instrumental to localize damage and understand destruction in disaster informatics. While convolutional neural networks are at the core of recent change detection solutions, we present in this work, BLDNet, a novel graph formulation for building damage change detection and enable learning relationships and representations from both local patterns and non-stationary neighborhoods. More specifically, we use graph convolutional networks to efficiently learn these features in a semi-supervised framework with few annotated data. Additionally, BLDNet formulation allows for the injection of additional contextual building meta-features. We train and benchmark on the xBD dataset to validate the effectiveness of our approach. We also demonstrate on urban data from the 2020 Beirut Port Explosion that performance is improved by incorporating domain knowledge building meta-features.