Robust Building Damage Detection in Cross-Disaster Settings Using Domain Adaptation

TL;DR

This paper presents a domain adaptation approach for building damage detection in remote sensing imagery, significantly improving robustness across different disaster-affected regions.

Contribution

It introduces a two-stage ensemble method with supervised domain adaptation, demonstrating its necessity and effectiveness in cross-disaster damage classification.

Findings

SDA is essential; without it, damage detection fails.

The pipeline achieves a Macro-F1 score of 0.5552 with SDA and unsharp-enhanced RGB inputs.

Systematic ablation shows the impact of augmentation components on performance.

Abstract

Rapid structural damage assessment from remote sensing imagery is essential for timely disaster response. Within human-machine systems (HMS) for disaster management, automated damage detection provides decision-makers with actionable situational awareness. However, models trained on multi-disaster benchmarks often underperform in unseen geographic regions due to domain shift - a distributional mismatch between training and deployment data that undermines human trust in automated assessments. We explore a two-stage ensemble approach using supervised domain adaptation (SDA) for building damage classification across four severity classes. The pipeline adapts the xView2 first-place method to the Ida-BD dataset using SDA and systematically investigates the effect of individual augmentation components on classification performance. Comprehensive ablation experiments on the unseen Ida-BD test split demonstrate that SDA is indispensable: removing it causes damage detection to fail entirely. Our pipeline achieves the most robust performance using SDA with unsharp-enhanced RGB input, attaining a Macro-F1 of 0.5552. These results underscore the critical role of domain adaptation in building trustworthy automated damage assessment modules for HMS-integrated disaster response.