A Hierarchical Decoder Architecture for Multilevel Fine-Grained Disaster Detection

As a cutting-edge challenge in the field of disaster evaluation, the detection of disasters in remote sensing images is crucial. However, most existing approaches to disaster detection simply solve the problem as a naive multiclass change detection (CD), lacking accurate damage-level classification. In this article, we propose a new approach to disaster detection called multilevel disaster detection (MLDD) that focuses on fine-grained damage-level classification. Our proposed approach tackles MLDD through hierarchical correlation modeling and presents a universal disaster detection architecture. Specifically, we summarize two existing applicative methods, one-step training and pretraining, which are compatible with our proposed architecture. In addition, we propose two novel hierarchical approaches, namely the multitask (MT)-based and graph-encoding (GE)-based approaches. The MT approach resolves MLDD through layerwise learning in a progressive manner, building explicit multistage and implicit joint models to probe into the coarse-to-fine correlation for damage-level evaluation. The GE approach enhances hierarchical relationships by encoding multifold messaging directions and probabilities using a graph neural network. Furthermore, all four hierarchical paradigms can be embedded in our hierarchical MLDD architecture, which outperforms the state-of-the-art methods on the xBD dataset, particularly in fine-grained damage-level classification. Overall, our proposed approach represents a significant improvement over existing disaster detection methods and has the potential to advance the field of disaster evaluation.