DUAL-TASKS SIAMESE TRANSFORMER FRAMEWORK FOR BUILDING DAMAGE ASSESSMENT

Accurate and fine-grained information about the extent of damage to buildings is essential for humanitarian relief and disaster response. However, as the most commonly used architecture in remote sensing interpretation tasks, Convolutional Neural Networks (CNNs) have limited ability to model the non-local relationship between pixels. Recently, Transformer architecture first proposed for modeling long-range dependency in natural language processing has shown promising results in computer vision tasks. Considering the frontier advances of Transformer architecture in the computer vision field, in this paper, we present a Transformerbased damage assessment architecture (DamFormer). In DamFormer, a siamese Transformer encoder is first constructed to extract non-local and representative deep features from input multitemporal image-pairs. Then, a multitemporal fusion module is designed to fuse information for downstream tasks. Finally, a lightweight dual-tasks decoder aggregates multi-level features for final prediction. To the best of our knowledge, it is the first time that such a deep Transformerbased network is proposed for multitemporal remote sensing interpretation tasks. The experimental results on the large-scale damage assessment dataset xBD demonstrate the potential of the Transformer-based architecture.

Automated summary

In this paper, a Transformer-based architecture called DamFormer is proposed for damage assessment. It utilizes a siamese Transformer encoder to extract non-local and representative deep features, a multitemporal fusion module to fuse information, and a lightweight dual-tasks decoder for final prediction. Experimental results demonstrate the potential of this Transformer-based architecture in remote sensing interpretation tasks.