DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhu, Kevin, Tang, William, Tene, Raphael Hay, Liu, Zesheng, Le, Nhut, Rahnemoonfar, Maryam
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910207570870272
author Zhu, Kevin
Tang, William
Tene, Raphael Hay
Liu, Zesheng
Le, Nhut
Rahnemoonfar, Maryam
author_facet Zhu, Kevin
Tang, William
Tene, Raphael Hay
Liu, Zesheng
Le, Nhut
Rahnemoonfar, Maryam
contents Rapid and accurate damage assessment following natural disasters is critical for effective emergency response. However, identifying fine-grained damage levels (e.g., distinguishing minor from major roof damage) in UAV imagery remains challenging due to the degradation of texture cues during resizing and extreme class imbalance. We propose DA-SegFormer, a damage-aware adaptation of the SegFormer architecture optimized for high-resolution disaster imagery. Our method introduces a Class-Aware Sampling strategy to guarantee exposure to rare damage features, and it integrates Online Hard Example Mining (OHEM) with Dice Loss to dynamically focus on underrepresented classes. In addition, we employ a resolution-preserving inference protocol that maintains native texture details. Evaluated on the RescueNet dataset, DA-SegFormer achieves 74.61\% mIoU, outperforming the baseline by 2.55\%. Notably, our improvements yield double-digit gains in critical damage classes: Minor Damage (+11.7%) and Major Damage (+21.3%).
format Preprint
id arxiv_https___arxiv_org_abs_2605_09864
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment
Zhu, Kevin
Tang, William
Tene, Raphael Hay
Liu, Zesheng
Le, Nhut
Rahnemoonfar, Maryam
Computer Vision and Pattern Recognition
Machine Learning
Rapid and accurate damage assessment following natural disasters is critical for effective emergency response. However, identifying fine-grained damage levels (e.g., distinguishing minor from major roof damage) in UAV imagery remains challenging due to the degradation of texture cues during resizing and extreme class imbalance. We propose DA-SegFormer, a damage-aware adaptation of the SegFormer architecture optimized for high-resolution disaster imagery. Our method introduces a Class-Aware Sampling strategy to guarantee exposure to rare damage features, and it integrates Online Hard Example Mining (OHEM) with Dice Loss to dynamically focus on underrepresented classes. In addition, we employ a resolution-preserving inference protocol that maintains native texture details. Evaluated on the RescueNet dataset, DA-SegFormer achieves 74.61\% mIoU, outperforming the baseline by 2.55\%. Notably, our improvements yield double-digit gains in critical damage classes: Minor Damage (+11.7%) and Major Damage (+21.3%).
title DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.09864