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

• URL: http://arxiv.org/abs/2605.09864v1
• Date: Mon, 11 May 2026 01:49:19 GMT
• Title: DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment
• Abstract summary: We propose DA-SegFormer, a damage-aware adaptation of the SegFormer architecture optimized for high-resolution disaster imagery.<n>Our method introduces a Class-Aware Sampling strategy to guarantee exposure to rare damage features.<n>It integrates Online Hard Example Mining (OHEM) with Dice Loss to dynamically focus on underrepresented classes.
• Score: 3.5487218173471184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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%).

Related papers

• Damage-TriageFormer: A Foundation-Model Framework for Typology-Based Building Damage Assessment from Mono-Temporal Imagery [7.078080152361472]
  This paper presents Damage-TriageFormer, a single-image, post-event, footprint-conditioned model that produces a damage typology rather than a severity scale.<n>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.
  arXiv  Detail & Related papers  (2026-06-10T15:50:54Z)
• Satellite to Street : Disaster Impact Estimator [0.12938914787881173]
  The present work proposes a deep-learning framework that jointly processes pre- and post-disaster satellite images to obtain fine-grained pixel-level damage maps: Satellite-to-Street: Disaster Impact Estimator.<n>The model uses a modified dual-input U-Net architecture with enhanced feature fusion to capture both the local structural changes as well as the broader contextual cues.
  arXiv  Detail & Related papers  (2025-11-24T06:20:40Z)
• Multi-Label Classification Framework for Hurricane Damage Assessment [1.8434042562191815]
  This paper introduces a novel multi-label classification framework for assessing damage using aerial imagery.<n>The proposed approach integrates a feature extraction module based on ResNet and a class-specific attention mechanism to identify multiple damage types within a single image.<n>Using the Rescuenet dataset from Hurricane Michael, the proposed method achieves a mean average precision of 90.23%, outperforming existing baseline methods.
  arXiv  Detail & Related papers  (2025-07-03T03:15:23Z)
• Post-Hurricane Debris Segmentation Using Fine-Tuned Foundational Vision Models [18.008592164636664]
  This work introduces an open-source dataset comprising approximately 1,200 manually annotated aerial RGB images from Hurricanes Ian, Ida, and Ike.<n>To mitigate human biases and enhance data quality, labels from multiple annotators are strategically aggregated and visual prompt engineering is employed.<n>The resulting fine-tuned model, named fCLIPSeg, achieves a Dice score of 0.70 on data from Hurricane Ida with virtually no false positives in debris-free areas.
  arXiv  Detail & Related papers  (2025-04-17T00:08:50Z)
• FaultGuard: A Generative Approach to Resilient Fault Prediction in Smart Electrical Grids [53.2306792009435]
  FaultGuard is the first framework for fault type and zone classification resilient to adversarial attacks. We propose a low-complexity fault prediction model and an online adversarial training technique to enhance robustness. Our model outclasses the state-of-the-art for resilient fault prediction benchmarking, with an accuracy of up to 0.958.
  arXiv  Detail & Related papers  (2024-03-26T08:51:23Z)
• 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation [92.17700318483745]
  We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
  arXiv  Detail & Related papers  (2023-11-27T07:57:29Z)
• Image Prior and Posterior Conditional Probability Representation for Efficient Damage Assessment [51.631659414455825]
  It is important to quantify Damage Assessment for Human Assistance and Disaster Response applications. In this paper, an image prior and posterior conditional probability (IP2CP) is developed as an effective computational imaging representation. The matching pre- and post-disaster images are effectively encoded into one image that is then processed using deep learning approaches to determine the damage levels.
  arXiv  Detail & Related papers  (2023-10-26T22:17:37Z)
• Robust Trajectory Prediction against Adversarial Attacks [84.10405251683713]
  Trajectory prediction using deep neural networks (DNNs) is an essential component of autonomous driving systems. These methods are vulnerable to adversarial attacks, leading to serious consequences such as collisions. In this work, we identify two key ingredients to defend trajectory prediction models against adversarial attacks.
  arXiv  Detail & Related papers  (2022-07-29T22:35:05Z)
• Attention Based Semantic Segmentation on UAV Dataset for Natural Disaster Damage Assessment [0.7614628596146599]
  We implement a novel self-attention based semantic segmentation model on a high resolution UAV dataset. The result inspires to use self-attention schemes in natural disaster damage assessment which will save human lives and reduce economic losses.
  arXiv  Detail & Related papers  (2021-05-30T13:39:03Z)
• Assessing out-of-domain generalization for robust building damage detection [78.6363825307044]
  Building damage detection can be automated by applying computer vision techniques to satellite imagery. Models must be robust to a shift in distribution between disaster imagery available for training and the images of the new event. We argue that future work should focus on the OOD regime instead.
  arXiv  Detail & Related papers  (2020-11-20T10:30:43Z)
• RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery [83.49145695899388]
  RescueNet is a unified model that can simultaneously segment buildings and assess the damage levels to individual buildings and can be trained end-to-end. RescueNet is tested on the large scale and diverse xBD dataset and achieves significantly better building segmentation and damage classification performance than previous methods.
  arXiv  Detail & Related papers  (2020-04-15T19:52:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.