Research map / Detection and segmentation / Open-set and few-shot detection
EIDSeg: A Pixel-Level Semantic Segmentation Dataset for Post-Earthquake Damage Assessment from Social Media Images
Huili Huang, Chengeng Liu, Danrong Zhang, Shail Patel, Anastasiya Masalava, Sagar Sadak, Parisa Babolhavaeji, WeiHong Low, Max Mahdi Roozbahani, J. David Frost
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 EoMT (1024 input) instead of OneFormer | semantic segmentation on EIDSeg · EIDSeg test | mIoU (%): 79.2 -> 80.8 | Improved |
| scale BEiT from ViT-B to ViT-L (ablation) | BEiT · EIDSeg test | mIoU (%): 77.7 -> 78.7 | Improved |
| scale Mask2Former from Swin-S to Swin-L (ablation) | Mask2Former · EIDSeg test | mIoU (%): 76.1 -> 77.4 | Improved |
| use transformer SegFormer instead of CNN DeepLabV3+ | segmentation backbone · EIDSeg test | mIoU (%): 67.1 -> 74.4 | Improved |
| use EIDSeg five-class data instead of DSS three-class data for SegFormer-B5 | SegFormer-B5 · mIoU | mIoU (%): 72 -> 74.4 | Improved |
| compare EoMT to OneFormer on D Road class | EoMT · EIDSeg test D Road IoU | IoU (%): 91.5 -> 87.3 | Hurt |
| higher input resolution 1024 for EoMT | EoMT · EIDSeg test | mIoU (%): 80.8 best overall | Improved |
Closest papers by meaning
- Generalizable Disaster Damage Assessment via Change Detection with Vision Foundation Model (AAAI 2025 · similarity 0.85)
- RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events (NeurIPS 2025 · similarity 0.83)
- DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response (NeurIPS 2025 · similarity 0.83)
- Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models (NeurIPS 2026 · similarity 0.83)
- MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing (NeurIPS 2025 · similarity 0.82)
- DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling (AAAI 2024 · similarity 0.81)
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.
