Reproduce “Uncertainty-Aware Regression for Socio-Economic Estimation via Multi-View Remote Sensing” 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
Fan Yang, Sahoko Ishida, Mengyan Zhang, Daniel Jenson, Swapnil Mishra, Jhonathan Navott, Seth Flaxman
The authors introduce a method combining interpretable three-band views of Sentinel-2 satellite imagery to estimate severe deprivation and uncertainty. Each view is encoded by a pretrained vision model, and its features are combined for prediction. On KidSat, four-view DINOv2 ViT-Base achieves mean absolute error 0.1605 ± 0.0020 versus 0.1663 ± 0.0023 for RGB, a modest gain limited to this task and setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.