6 citations · 15 across the 24 of their papers we have counts for
27 papers
Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute Backend
Satej S. Soman, Akram Zaytar, Girmaw A. Tadesse +5
Applying deep learning models to satellite imagery from within geographic information systems (GIS) remains high-friction for remote sensing practitioners. Models arrive in incompa…
WATCH: Wide-Area Archaeological Site Tracking for Change Detection
Girmaw Abebe Tadesse, Titien Bartette, Andrew Hassanali +7
Monitoring archaeological sites at scale is vital for protecting cultural heritage, yet pinpointing when disturbances occur remains difficult because visual cues are subtle and gro…
GeoAI Agency Primitives
Akram Zaytar, Rohan Sawahn, Caleb Robinson +5
We present ongoing research on agency primitives for GeoAI assistants -- core capabilities that connect Foundation models to the artifact-centric, human-in-the-loop workflows where…
TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery
Tammy Glazer, Gilles Q. Hacheme, Akram Zaytar +9
We present TEMPO, a global, temporally resolved dataset of building density and height derived from high-resolution satellite imagery using deep learning models. We pair building f…
Machine Learning for Sustainable Rice Production: Region-Scale Monitoring of Water-Saving Practices in Punjab, India
Ando Shah, Rajveer Singh, Akram Zaytar +6
Rice cultivation supplies half the world's population with staple food, while also being a major driver of freshwater depletion--consuming roughly a quarter of global freshwater--a…
Optimizing Cloud-to-GPU Throughput for Deep Learning With Earth Observation Data
Akram Zaytar, Caleb Robinson, Girmaw Abebe Tadesse +5
Training deep learning models on petabyte-scale Earth observation (EO) data requires separating compute resources from data storage. However, standard PyTorch data loaders cannot k…
GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models
Gilles Quentin Hacheme, Girmaw Abebe Tadesse, Caleb Robinson +3
Classifying geospatial imagery remains a major bottleneck for applications such as disaster response and land-use monitoring-particularly in regions where annotated data is scarce…
Sims: An Interactive Tool for Geospatial Matching and Clustering
Akram Zaytar, Girmaw Abebe Tadesse, Caleb Robinson +6
Acquiring, processing, and visualizing geospatial data requires significant computing resources, especially for large spatio-temporal domains. This challenge hinders the rapid disc…
Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps
Girmaw Abebe Tadesse, Caleb Robinson, Charles Mwangi +7
In 2023, 58.0% of the African population experienced moderate to severe food insecurity, with 21.6% facing severe food insecurity. Land-use and land-cover maps provide crucial insi…
Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation
Burak Ekim, Girmaw Abebe Tadesse, Caleb Robinson +4
Training robust deep learning models is crucial in Earth Observation, where globally deployed models often face distribution shifts that degrade performance, especially in low-data…
AI and the Future of Work in Africa White Paper
Jacki O'Neill, Vukosi Marivate, Barbara Glover +71
This white paper is the output of a multidisciplinary workshop in Nairobi (Nov 2023). Led by a cross-organisational team including Microsoft Research, NEPAD, Lelapa AI, and Univers…
Analyzing Decades-Long Environmental Changes in Namibia Using Archival Aerial Photography and Deep Learning
Girmaw Abebe Tadesse, Caleb Robinson, Gilles Quentin Hacheme +5
This study explores object detection in historical aerial photographs of Namibia to identify long-term environmental changes. Specifically, we aim to identify key objects -- Waterh…
Bootstrapping Rare Object Detection in High-Resolution Satellite Imagery
Akram Zaytar, Caleb Robinson, Gilles Q. Hacheme +6
Rare object detection is a fundamental task in applied geospatial machine learning, however is often challenging due to large amounts of high-resolution satellite or aerial imagery…
Weak Labeling for Cropland Mapping in Africa
Gilles Quentin Hacheme, Akram Zaytar, Girmaw Abebe Tadesse +4
Cropland mapping can play a vital role in addressing environmental, agricultural, and food security challenges. However, in the context of Africa, practical applications are often…
Efficient Representation of the Activation Space in Deep Neural Networks
Tanya Akumu, Celia Cintas, Girmaw Abebe Tadesse +3
The representations of the activation space of deep neural networks (DNNs) are widely utilized for tasks like natural language processing, anomaly detection and speech recognition.…
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
Luis Oala, Manil Maskey, Lilith Bat-Leah +35
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure developm…
Domain-agnostic and Multi-level Evaluation of Generative Models
Girmaw Abebe Tadesse, Jannis Born, Celia Cintas +4
While the capabilities of generative models heavily improved in different domains (images, text, graphs, molecules, etc.), their evaluation metrics largely remain based on simplifi…
BON: An extended public domain dataset for human activity recognition
Girmaw Abebe Tadesse, Oliver Bent, Komminist Weldemariam +3
Body-worn first-person vision (FPV) camera enables to extract a rich source of information on the environment from the subject's viewpoint. However, the research progress in wearab…
Model-free feature selection to facilitate automatic discovery of divergent subgroups in tabular data
Girmaw Abebe Tadesse, William Ogallo, Celia Cintas +1
Data-centric AI encourages the need of cleaning and understanding of data in order to achieve trustworthy AI. Existing technologies, such as AutoML, make it easier to design and tr…
Sparsity-based Feature Selection for Anomalous Subgroup Discovery
Girmaw Abebe Tadesse, William Ogallo, Catherine Wanjiru +5
Anomalous pattern detection aims to identify instances where deviation from normalcy is evident, and is widely applicable across domains. Multiple anomalous detection techniques ha…
Post-discovery Analysis of Anomalous Subsets
Isaiah Onando Mulang', William Ogallo, Girmaw Abebe Tadesse +1
Analyzing the behaviour of a population in response to disease and interventions is critical to unearth variability in healthcare as well as understand sub-populations that require…
Automated Supervised Feature Selection for Differentiated Patterns of Care
Catherine Wanjiru, William Ogallo, Girmaw Abebe Tadesse +3
An automated feature selection pipeline was developed using several state-of-the-art feature selection techniques to select optimal features for Differentiating Patterns of Care (D…
Out-of-Distribution Detection in Dermatology using Input Perturbation and Subset Scanning
Hannah Kim, Girmaw Abebe Tadesse, Celia Cintas +2
Recent advances in deep learning have led to breakthroughs in the development of automated skin disease classification. As we observe an increasing interest in these models in the…
Pattern Detection in the Activation Space for Identifying Synthesized Content
Celia Cintas, Skyler Speakman, Girmaw Abebe Tadesse +3
Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize…