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

arXiv: https://arxiv.org/abs/2603.14694 · HTML: https://mlsanity.com/paper/2603.14694/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 28 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [xBD: A Dataset for Assessing Building Damage from Satellite Imagery](https://mlsanity.com/paper/1911.09296/) (2019)
- [Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data](https://mlsanity.com/paper/2104.07778/) (2021)
- [BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images](https://mlsanity.com/paper/2105.07364/) (2021)
- [An Attention-Based System for Damage Assessment Using Satellite Imagery](https://mlsanity.com/paper/2004.06643/) (2020)
- [Fully convolutional Siamese neural networks for buildings damage assessment from satellite images](https://mlsanity.com/paper/2111.00508/) (2021)
- [A simple, strong baseline for building damage detection on the xBD dataset](https://mlsanity.com/paper/2401.17271/) (2024)

## Built on by (most cited first, 4 of 4)

- [Demographic-Aware Transfer Learning for Sleep Stage Classification in Clinical Polysomnography](https://mlsanity.com/paper/2605.02245/) (2026)
- [STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification](https://mlsanity.com/paper/2605.06736/) (2026)
- [NanoSleep: A Parameter-Efficient Hybrid Temporal Convolutional Network for Single-Channel Sleep Stage Classification](https://mlsanity.com/paper/2608.18571/) (2026)
- [Shortcut Learning in Geospatial Foundation Model Embeddings for Cross-Disaster Damage Assessment](https://mlsanity.com/paper/2610.13766/) (2026)

## Abstract (arXiv)

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.