AI RESEARCH
EarthShift: a benchmark for measuring robustness to real-world distribution shifts in Earth observation
arXiv CS.CV
•
ArXi:2605.29330v1 Announce Type: new Current Earth observation benchmarks focus on measuring performance on diverse tasks and applications, typically measuring generalization in-distribution. But when models are deployed, they must generalize to myriad out-of-distribution scenarios, such as new time periods, geographies, scales, and sensors. We