4 papers · 1 filter
OT on the Map: Quantifying Domain Shifts in Geographic Space
Haoran Zhang, Livia Betti, Konstantin Klemmer +2
In computer vision and machine learning for geographic data, out-of-domain generalization is a pervasive challenge, arising from uneven global data coverage and distribution shifts…
Measuring the Intrinsic Dimension of Earth Representations
Arjun Rao, Marc RuÃwurm, Konstantin Klemmer +1
Within the context of representation learning for Earth observation, geographic Implicit Neural Representations (INRs) embed low-dimensional location inputs (longitude, latitude) i…
Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks
Marc RuÃwurm, Konstantin Klemmer, Esther Rolf +2
Learning representations of geographical space is vital for any machine learning model that integrates geolocated data, spanning application domains such as remote sensing, ecology…
Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning
Esther Rolf, Konstantin Klemmer, Caleb Robinson +1
Satellite data has the potential to inspire a seismic shift for machine learning -- one in which we rethink existing practices designed for traditional data modalities. As machine…