Research map / Large language models / AI and society
A Benchmark Dataset for Spatially Aligned Road Damage Assessment in Small Uncrewed Aerial Systems Disaster Imagery
Thomas Manzini, Priyankari Perali, Raisa Karnik, Robin R. Murphy
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use spatially aligned (adjusted) road lines instead of unadjusted (ablation) | 8 baseline models · Simple task | IoU_km: average degradation 0.014 IoU_km when unadjusted | Improved |
| use adjusted road lines on Full task (ablation) | 8 baseline models · Full task | IoU_km: average degradation 0.0003 IoU_km | No clear effect |
| use adjusted road lines on UNet with Attention (ablation) | UNet with Attention · Simple task | IoU_km: 0.312 -> 0.331 | Improved |
| add attention to UNet (ablation) | UNet · Simple task | macro IoU_km: 0.307 -> 0.331 | Improved |
| use pretrained ViT encoder with Segmenter (ablation) | ViT-L + Segmenter · Simple task | macro IoU_km: 0.039 -> 0.015 | Hurt |
| use pretrained ViT encoder with UperNet (ablation) | ViT-L + UperNet · Simple task | macro IoU_km: 0.211 -> 0.209 | No clear effect |
| increase number of prediction classes from Simple to Full | All baseline models · CRASAR-U-DROIDs | macro IoU_km: 0.331 -> 0.091 (UNet with Attention) | Hurt |
| deploy Attention UNet Simple model in Hurricanes Debby and Helene | UNet with Attention · operational deployment | qualitative practitioner feedback | Improved |
Closest papers by meaning
- Generalizable Disaster Damage Assessment via Change Detection with Vision Foundation Model (AAAI 2025 · similarity 0.86)
- DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response (NeurIPS 2025 · similarity 0.85)
- Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations (NeurIPS 2026 · similarity 0.84)
- MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing (NeurIPS 2025 · similarity 0.82)
- Flood Insights: Integrating Remote and Social Sensing Data for Flood Exposure, Damage, and Urgent Needs Mapping (AAAI 2024 · similarity 0.82)
- DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling (AAAI 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
