# Damage-TriageFormer: A Foundation-Model Framework for Typology-Based Building Damage Assessment from Mono-Temporal Imagery

arXiv: https://arxiv.org/abs/2606.12248 · HTML: https://mlsanity.com/paper/2606.12248/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [xBD: A Dataset for Assessing Building Damage from Satellite Imagery](https://mlsanity.com/paper/1911.09296/) (2019)
- [ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model](https://mlsanity.com/paper/2404.03425/) (2024)
- [Large-scale Building Damage Assessment using a Novel Hierarchical Transformer Architecture on Satellite Images](https://mlsanity.com/paper/2208.02205/) (2022)
- [BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images](https://mlsanity.com/paper/2105.07364/) (2021)
- [SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images](https://mlsanity.com/paper/2208.00657/) (2022)
- [Generalizable Disaster Damage Assessment via Change Detection with Vision Foundation Model](https://mlsanity.com/paper/2406.08020/) (2024)
- [DamageCAT: A Deep Learning Transformer Framework for Typology-Based Post-Disaster Building Damage Categorization](https://mlsanity.com/paper/2504.11637/) (2025)
- [DeepDamageNet: A two-step deep-learning model for multi-disaster building damage segmentation and classification using satellite imagery](https://mlsanity.com/paper/2405.04800/) (2024)
- [Self-Supervised Learning for Building Damage Assessment from Large-scale xBD Satellite Imagery Benchmark Datasets](https://mlsanity.com/paper/2205.15688/) (2022)
- [Post-hurricane building damage assessment using street-view imagery and structured data: A multi-modal deep learning approach](https://mlsanity.com/paper/2404.07399/) (2024)
- [MTBF-33: A multi-temporal building footprint dataset for 33 counties in the United States (1900-2015)](https://mlsanity.com/paper/2203.11078/) (2022)
- [Building Damage Detection using Satellite Images and Patch-Based Transformer Methods](https://mlsanity.com/paper/2602.08117/) (2026)

## Built on by (most cited first, 1 of 1)

- [HASTE: A Platform for Rapid Post-Disaster Building Damage Assessment](https://mlsanity.com/paper/2607.11838/) (2026)

## Abstract (arXiv)

Decision-relevant building damage assessment is critical for prioritizing resources and recovery after a disaster, yet most automated methods either flatten damage into a single severity scale (no damage, minor, major, destroyed) or require paired pre- and post-event imagery that is often unavailable for emerging hazards. This paper presents Damage-TriageFormer, a single-image, post-event, footprint-conditioned model that produces a damage typology rather than a severity scale. We contribute: (1) DamageTriage-Bench, a new benchmark built from NOAA Emergency Response Imagery across Hurricane Michael (2018), Hurricane Helene (2024), and the 2025 Los Angeles wildfire complex, with five typology classes that distinguish roof damage from structural damage and, within each, partial from total extent; and (2) Damage-TriageFormer, which extends a DINOv3 ViT-L backbone with a Simple Feature Pyramid for higher-resolution instance pooling, a two-stage gated damage head, and an auxiliary severity-regression objective. Our model achieves macro F1 of 0.624 on validation and 0.619 on a held-out stratified test set, performing strongest where operational triage needs it most, with per-class F1 of 0.91 and 0.84 on undamaged buildings and total structural collapse, respectively. While the rare Total Roof Damage class remains difficult due to its limited examples and an inherently ambiguous label boundary, our results show that single-image post-event imagery can support actionable building damage typing, enabling targeted emergency response and resource allocation without a pre-event reference.