Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Mejia, Joseph"'
Accurately estimating forest biomass is crucial for global carbon cycle modelling and climate change mitigation. Tree height, a key factor in biomass calculations, can be measured using Synthetic Aperture Radar (SAR) technology. This study applies ma
Externí odkaz:
http://arxiv.org/abs/2409.05636
This paper introduces a novel anomaly detection framework that combines the robust statistical principles of density-estimation-based anomaly detection methods with the representation-learning capabilities of deep learning models. The method originat
Externí odkaz:
http://arxiv.org/abs/2408.07623
Autor:
Allen, Matthew J, Dorr, Francisco, Mejia, Joseph Alejandro Gallego, Martínez-Ferrer, Laura, Jungbluth, Anna, Kalaitzis, Freddie, Ramos-Pollán, Raúl
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 processing these large datasets for use in ML pipelines is technicall
Externí odkaz:
http://arxiv.org/abs/2406.04230
Autor:
Gallego-Mejia, Joseph A., Jungbluth, Anna, Martínez-Ferrer, Laura, Allen, Matt, Dorr, Francisco, Kalaitzis, Freddie, Ramos-Pollán, Raúl
Self-supervised learning (SSL) models have recently demonstrated remarkable performance across various tasks, including image segmentation. This study delves into the emergent characteristics of the Self-Distillation with No Labels (DINO) algorithm a
Externí odkaz:
http://arxiv.org/abs/2310.03513
Autor:
Martínez-Ferrer, Laura, Jungbluth, Anna, Gallego-Mejia, Joseph A., Allen, Matt, Dorr, Francisco, Kalaitzis, Freddie, Ramos-Pollán, Raúl
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 on smaller labeled datasets to predict vegetation percentage, and empir
Externí odkaz:
http://arxiv.org/abs/2310.02048
Autor:
Allen, Matt, Dorr, Francisco, Gallego-Mejia, Joseph A., Martínez-Ferrer, Laura, Jungbluth, Anna, Kalaitzis, Freddie, Ramos-Pollán, Raúl
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 sensors can be used to inform intervention and policy decision making
Externí odkaz:
http://arxiv.org/abs/2310.00826
Autor:
Allen, Matt, Dorr, Francisco, Gallego-Mejia, Joseph A., Martínez-Ferrer, Laura, Jungbluth, Anna, Kalaitzis, Freddie, Ramos-Pollán, Raúl
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 interferom
Externí odkaz:
http://arxiv.org/abs/2310.00119
This paper introduces a novel approach to probabilistic deep learning, kernel density matrices, which provide a simpler yet effective mechanism for representing joint probability distributions of both continuous and discrete random variables. In quan
Externí odkaz:
http://arxiv.org/abs/2305.18204
This paper presents an anomaly detection model that combines the strong statistical foundation of density-estimation-based anomaly detection methods with the representation-learning ability of deep-learning models. The method combines an autoencoder,
Externí odkaz:
http://arxiv.org/abs/2211.08525
This paper presents a novel density estimation method for anomaly detection using density matrices (a powerful mathematical formalism from quantum mechanics) and Fourier features. The method can be seen as an efficient approximation of Kernel Density
Externí odkaz:
http://arxiv.org/abs/2210.14796