Cross-directional Feature Fusion Network for Building Damage Assessment from Satellite Imagery
This addresses the problem of fast and effective disaster response for emergency responders, but it appears incremental as it builds on existing methods with a novel fusion strategy.
The paper tackles building damage assessment from satellite imagery by proposing a cross-directional fusion strategy to explore correlations between pre- and post-disaster images, achieving state-of-the-art performance on the xBD dataset.
Fast and effective responses are required when a natural disaster (e.g., earthquake, hurricane, etc.) strikes. Building damage assessment from satellite imagery is critical before an effective response is conducted. High-resolution satellite images provide rich information with pre- and post-disaster scenes for analysis. However, most existing works simply use pre- and post-disaster images as input without considering their correlations. In this paper, we propose a novel cross-directional fusion strategy to better explore the correlations between pre- and post-disaster images. Moreover, the data augmentation method CutMix is exploited to tackle the challenge of hard classes. The proposed method achieves state-of-the-art performance on a large-scale building damage assessment dataset -- xBD.