409 citations · 1.2k across the 27 of their papers we have counts for
12 papers · 1 filter
Zero-Shot Satellite Image Retrieval through Joint Embeddings: Application to Crisis Response
James Walsh, William Fawcett, Grace Colverd +1
Semantic search of Earth observation archives remains challenging. Visual foundation models such as CLAY produce rich embeddings of satellite imagery but lack the natural-language…
Rapid Adaptation of Earth Observation Foundation Models for Segmentation
Karthick Panner Selvam, Raul Ramos-Pollan, Freddie Kalaitzis
This study investigates the efficacy of Low-Rank Adaptation (LoRA) in fine-tuning Earth Observation (EO) foundation models for flood segmentation. We hypothesize that LoRA, a param…
Uncertainty and Generalizability in Foundation Models for Earth Observation
Raul Ramos-Pollan, Freddie Kalaitzis, Karthick Panner Selvam
We take the perspective in which we want to design a downstream task (such as estimating vegetation coverage) on a certain area of interest (AOI) with a limited labeling budget. By…
M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and Multispectral Data
Matthew J Allen, Francisco Dorr, Joseph Alejandro Gallego Mejia +4
Satellite-based remote sensing has revolutionised the way we address global challenges. Huge quantities of Earth Observation (EO) data are generated by satellite sensors daily, but…
Exploring DINO: Emergent Properties and Limitations for Synthetic Aperture Radar Imagery
Joseph A. Gallego-Mejia, Anna Jungbluth, Laura Martínez-Ferrer +4
Self-supervised learning (SSL) models have recently demonstrated remarkable performance across various tasks, including image segmentation. This study delves into the emergent char…
Exploring Generalisability of Self-Distillation with No Labels for SAR-Based Vegetation Prediction
Laura Martínez-Ferrer, Anna Jungbluth, Joseph A. Gallego-Mejia +4
In this work we pre-train a DINO-ViT based model using two Synthetic Aperture Radar datasets (S1GRD or GSSIC) across three regions (China, Conus, Europe). We fine-tune the models o…
Large Scale Masked Autoencoding for Reducing Label Requirements on SAR Data
Matt Allen, Francisco Dorr, Joseph A. Gallego-Mejia +4
Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change. Large scale, high resolution data derived from these…
Fewshot learning on global multimodal embeddings for earth observation tasks
Matt Allen, Francisco Dorr, Joseph A. Gallego-Mejia +4
In this work we pretrain a CLIP/ViT based model using three different modalities of satellite imagery across five AOIs covering over ~10\% of Earth's total landmass, namely Sentine…
On-orbit model training for satellite imagery with label proportions
Raúl Ramos-Pollán, Fabio A. González
This work addresses the challenge of training supervised machine or deep learning models on orbiting platforms where we are generally constrained by limited on-board hardware capab…
Enhancing Self-Supervised Learning for Remote Sensing with Elevation Data: A Case Study with Scarce And High Level Semantic Labels
Omar A. Castaño-Idarraga, Raul Ramos-Pollán, Freddie Kalaitzis
This work proposes a hybrid unsupervised and supervised learning method to pre-train models applied in Earth observation downstream tasks when only a handful of labels denoting ver…
Deep learning based landslide density estimation on SAR data for rapid response
Vanessa Boehm, Wei Ji Leong, Ragini Bal Mahesh +5
This work aims to produce landslide density estimates using Synthetic Aperture Radar (SAR) satellite imageries to prioritise emergency resources for rapid response. We use the Unit…
SAR-based landslide classification pretraining leads to better segmentation
Vanessa Böhm, Wei Ji Leong, Ragini Bal Mahesh +5
Rapid assessment after a natural disaster is key for prioritizing emergency resources. In the case of landslides, rapid assessment involves determining the extent of the area affec…