4 papers
What's in an Earth Embedding? An Explainability Analysis of Location Encoders
Livia Betti, Sebastian Ricke, Ivica Obadic +2
Geographic implicit neural representations (INRs) learn to map any coordinate on Earth to a location embedding, implicitly encoding geospatial data into the weights of a neural net…
Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
Amandeep Kaur, Mirali Purohit, Gedeon Muhawenayo +2
New geospatial foundation models introduce a new model architecture and pretraining dataset, often sampled using different notions of data diversity. Performance differences are la…
How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models?
Mirali Purohit, Gedeon Muhawenayo, Esther Rolf +1
Foundation models have made rapid advances in many domains including Earth observation, where Geospatial Foundation Models (GFMs) can help address global challenges such as climate…
Classification Drives Geographic Bias in Street Scene Segmentation
Rahul Nair, Gabriel Tseng, Esther Rolf +2
Previous studies showed that image datasets lacking geographic diversity can lead to biased performance in models trained on them. While earlier work studied general-purpose image…