A new spatial affinity component for self-supervised pretraining leverages high-resolution imagery to enhance mid-resolution satellite image representations and segmentation performance.
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, 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.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
TESSERA learns robust label-efficient embeddings from irregular multi-modal EO time series via Barlow Twins plus global shuffling and mix-based regularizers, delivering SOTA accuracy on classification, segmentation and regression tasks while releasing planetary-scale embeddings and code.
MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.
Remote-sensing foundation models need domain-specific design and evaluation around measurement physics and decision constraints; benchmark accuracy alone is insufficient for trustworthy EO deployment.
citing papers explorer
-
Cross-Scale Pretraining: Enhancing Self-Supervised Learning for Low-Resolution Satellite Imagery for Semantic Segmentation
A new spatial affinity component for self-supervised pretraining leverages high-resolution imagery to enhance mid-resolution satellite image representations and segmentation performance.
-
TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
TESSERA learns robust label-efficient embeddings from irregular multi-modal EO time series via Barlow Twins plus global shuffling and mix-based regularizers, delivering SOTA accuracy on classification, segmentation and regression tasks while releasing planetary-scale embeddings and code.
-
MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications
MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.
-
Scalable and Trustworthy Earth Observation Foundation Models
Remote-sensing foundation models need domain-specific design and evaluation around measurement physics and decision constraints; benchmark accuracy alone is insufficient for trustworthy EO deployment.