Reproduce “HASTE: A Platform for Rapid Post-Disaster Building Damage Assessment” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Caleb Robinson, Anthony Ortiz, Simone Fobi Nsutezo, Cameron Birge, Meygha Machado, Marcelo Duarte, Joaquin Rivero Rodriguez, Anthony Cintron Roman and 3 more
HASTE lets responders label a post-disaster scene and map building damage. It offers scene-trained U-Net segmentation or footprint embeddings with a classifier. Workflows supported 31 events within hours to days. In xBD testing, Method 2 reached 0.91 ± 0.005 macro ROC-AUC with 10% labels versus 0.88 ± 0.006 for ResNet-50 with all labels; this benchmark does not establish operational accuracy.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.