Portrait of Marlena Reil

Marlena Reil

Master's Research - McGill University
Supervisor
David Rolnick
Research Topics
Computer Vision
Deep Learning
GitHub

Publications

Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
Gabriel Tseng
Anthony Fuller
Marlena Reil
Henry Herzog
Patrick Beukema
Favyen Bastani
James R Green
Evan Shelhamer
Hannah Kerner
David Rolnick
We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, … (see more)elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and fast) to glaciers (thousands of pixels and slow). We present a novel self-supervised learning algorithm that extracts multi-scale features across a flexible set of input modalities through masked modeling. Our dual global and local contrastive losses differ in their targets (deep representations vs. shallow input projections) and masking strategies (structured vs. not). Our Galileo is a single generalist model that outperforms SoTA specialist models for satellite images and pixel time series across eleven benchmarks and multiple tasks.
2025-10-06
Proceedings of the 42nd International Conference on Machine Learning (published)
proceedings.mlr.press
Galileo: Learning Global&Local Features of Many Remote Sensing Modalities
Gabriel Tseng
Anthony Fuller
Marlena Reil
Henry Herzog
Patrick Beukema
Favyen Bastani
James R Green
Evan Shelhamer
Hannah Kerner
David Rolnick
We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, … (see more)elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and fast) to glaciers (thousands of pixels and slow). We present a novel self-supervised learning algorithm that extracts multi-scale features across a flexible set of input modalities through masked modeling. Our dual global and local contrastive losses differ in their targets (deep representations vs. shallow input projections) and masking strategies (structured vs. not). Our Galileo is a single generalist model that outperforms SoTA specialist models for satellite images and pixel time series across eleven benchmarks and multiple tasks.
2025-05-01
ICML.cc/2025/Conference (poster)
proceedings.mlr.press
openreview.net
Galileo: Learning Global and Local Features in Pretrained Remote Sensing Models
Gabriel Tseng
A. Fuller
Marlena Reil
Henry Herzog
Patrick Beukema
Favyen Bastani
James R. Green
Evan Shelhamer
Hannah Kerner
David Rolnick
From crop mapping to flood detection, machine learning in remote sensing has a wide range of societally beneficial applications. The commona… (see more)lities between remote sensing data in these applications present an opportunity for pretrained machine learning models tailored to remote sensing to reduce the labeled data and effort required to solve individual tasks. However, such models must be: (i) flexible enough to ingest input data of varying sensor modalities and shapes (i.e., of varying spatial and temporal dimensions), and (ii) able to model Earth surface phenomena of varying scales and types. To solve this gap, we present Galileo, a family of pretrained remote sensing models designed to flexibly process multimodal remote sensing data. We also introduce a novel and highly effective self-supervised learning approach to learn both large- and small-scale features, a challenge not addressed by previous models. Our Galileo models obtain state-of-the-art results across diverse remote sensing tasks.
2025-02-13
ArXiv (preprint)
arxiv.org
arxiv.org
Galileo: Learning Global and Local Features in Pretrained Remote Sensing Models
Gabriel Tseng
Anthony Fuller
Marlena Reil
Henry Herzog
Patrick Beukema
Favyen Bastani
James R Green
Evan Shelhamer
Hannah Kerner
David Rolnick
From crop mapping to flood detection, machine learning in remote sensing has a wide range of societally beneficial applications. The commona… (see more)lities between remote sensing data in these applications present an opportunity for pretrained machine learning models tailored to remote sensing to reduce the labeled data and effort required to solve individual tasks. However, such models must be: (i) flexible enough to ingest input data of varying sensor modalities and shapes (i.e., of varying spatial and temporal dimensions), and (ii) able to model Earth surface phenomena of varying scales and types. To solve this gap, we present Galileo, a family of pretrained remote sensing models designed to flexibly process multimodal remote sensing data. We also introduce a novel and highly effective self-supervised learning approach to learn both large- and small-scale features, a challenge not addressed by previous models. Our Galileo models obtain state-of-the-art results across diverse remote sensing tasks.
2025-02-13
ArXiv (preprint)
doi.org
arxiv.org
Galileo: Learning Global&Local Features of Many Remote Sensing Modalities
Gabriel Tseng
A. Fuller
Marlena Reil
Henry Herzog
Patrick Beukema
Favyen Bastani
James R. Green
Evan Shelhamer
Hannah Kerner
David Rolnick
We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, … (see more)elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and transient) to glaciers (thousands of pixels and persistent). We present a novel self-supervised learning algorithm that extracts multi-scale features across a flexible set of input modalities through masked modeling. Our dual global and local contrastive losses differ in their targets (deep representations vs. shallow input projections) and masking strategies (structured vs. not). Our Galileo is a single generalist model that outperforms SoTA specialist models for satellite images and pixel time series across eleven benchmarks and multiple tasks.
2025-02-13
ArXiv (preprint)
arxiv.org
arxiv.org