3 papers
cs.CV2024
Evaluating and Benchmarking Foundation Models for Earth Observation and Geospatial AI
Nikolaos Dionelis, Casper Fibaek, Luke Camilleri +3
When we are primarily interested in solving several problems jointly with a given prescribed high performance accuracy for each target application, then Foundation Models should fo…
cs.CV2024
Learning from Unlabelled Data with Transformers: Domain Adaptation for Semantic Segmentation of High Resolution Aerial Images
Nikolaos Dionelis, Francesco Pro, Luca Maiano +2
Data from satellites or aerial vehicles are most of the times unlabelled. Annotating such data accurately is difficult, requires expertise, and is costly in terms of time. Even if…
cs.CV2024
PhilEO Bench: Evaluating Geo-Spatial Foundation Models
Casper Fibaek, Luke Camilleri, Andreas Luyts +2
Massive amounts of unlabelled data are captured by Earth Observation (EO) satellites, with the Sentinel-2 constellation generating 1.6 TB of data daily. This makes Remote Sensing a…