Search Results for author:
Found 6 papers, 2 papers with code
Exploring DINO: Emergent Properties and Limitations for Synthetic Aperture Radar Imagery
We observe a small improvement in model performance with pre-training compared to training from scratch and discuss the limitations and opportunities of SSL for remote sensing and land cover segmentation.
Exploring Generalisability of Self-Distillation with No Labels for SAR-Based Vegetation Prediction
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).
Large Scale Masked Autoencoding for Reducing Label Requirements on SAR Data
Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change.
Fewshot learning on global multimodal embeddings for earth observation tasks
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 Sentinel 2 RGB optical imagery, Sentinel 1 SAR radar amplitude and interferometric coherence.
On-orbit model training for satellite imagery with label proportions
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 capabilities and restricted uplink bandwidths to upload.
Kernel Density Matrices for Probabilistic Deep Learning
In doing so, we provide a versatile representation of marginal and joint probability distributions that allows us to develop a differentiable, compositional, and reversible inference procedure that covers a wide range of machine learning tasks, including density estimation, discriminative learning, and generative modeling.
