AI Paper Atlas

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

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
use EoMT (1024 input) instead of OneFormersemantic segmentation on EIDSeg · EIDSeg testmIoU (%): 79.2 -> 80.8Improved
scale BEiT from ViT-B to ViT-L (ablation)BEiT · EIDSeg testmIoU (%): 77.7 -> 78.7Improved
scale Mask2Former from Swin-S to Swin-L (ablation)Mask2Former · EIDSeg testmIoU (%): 76.1 -> 77.4Improved
use transformer SegFormer instead of CNN DeepLabV3+segmentation backbone · EIDSeg testmIoU (%): 67.1 -> 74.4Improved
use EIDSeg five-class data instead of DSS three-class data for SegFormer-B5SegFormer-B5 · mIoUmIoU (%): 72 -> 74.4Improved
compare EoMT to OneFormer on D Road classEoMT · EIDSeg test D Road IoUIoU (%): 91.5 -> 87.3Hurt
higher input resolution 1024 for EoMTEoMT · EIDSeg testmIoU (%): 80.8 best overallImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy