6 papers
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…
PRUE: A Practical Recipe for Field Boundary Segmentation at Scale
Gedeon Muhawenayo, Caleb Robinson, Subash Khanal +10
Large-scale maps of field boundaries are essential for agricultural monitoring tasks. Existing deep learning approaches for satellite-based field mapping are sensitive to illuminat…
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…
An All-MLP Sequence Modeling Architecture That Excels at Copying
Chenwei Cui, Zehao Yan, Gedeon Muhawenayo +1
Recent work demonstrated Transformers' ability to efficiently copy strings of exponential sizes, distinguishing them from other architectures. We present the Causal Relation Networ…
Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing
Alexandre Zouaoui, Gedeon Muhawenayo, Behnood Rasti +2
In this paper, we introduce a new algorithm based on archetypal analysis for blind hyperspectral unmixing, assuming linear mixing of endmembers. Archetypal analysis is a natural fo…
Compressed Object Detection
Gedeon Muhawenayo, Georgia Gkioxari
Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have mil…