Improved MambdaBDA Framework for Robust Building Damage Assessment Across Disaster Domains

TL;DR

This paper enhances the MambaBDA building damage assessment network with modular components to improve accuracy and generalization across various disaster domains using satellite imagery.

Contribution

It introduces three modular enhancements—Focal Loss, Attention Gates, and an Alignment Module—to improve robustness and cross-dataset performance of BDA models.

Findings

Performance gains of 0.8% to 5% in-domain

Up to 27% improvement on unseen disasters

Enhanced generalization across multiple datasets

Abstract

Reliable post-disaster building damage assessment (BDA) from satellite imagery is hindered by severe class imbalance, background clutter, and domain shift across disaster types and geographies. In this work, we address these problems and explore ways to improve the MambaBDA, the BDA network of ChangeMamba architecture, one of the most successful BDA models. The approach enhances the MambaBDA with three modular components: (i) Focal Loss to mitigate class imbalance damage classification, (ii) lightweight Attention Gates to suppress irrelevant context, and (iii) a compact Alignment Module to spatially warp pre-event features toward post-event content before decoding. We experiment on multiple satellite imagery datasets, including xBD, Pakistan Flooding, Turkey Earthquake, and Ida Hurricane, and conduct in-domain and crossdataset tests. The proposed modular enhancements yield consistent improvements over the baseline model, with 0.8% to 5% performance gains in-domain, and up to 27% on unseen disasters. This indicates that the proposed enhancements are especially beneficial for the generalization capability of the system.