MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data

K Kikaki, I Kakogeorgiou, P Mikeli, DE Raitsos… - PloS one, 2022 - journals.plos.org
Currently, a significant amount of research is focused on detecting Marine Debris and
assessing its spectral behaviour via remote sensing, ultimately aiming at new operational …

Omnisat: Self-supervised modality fusion for earth observation

G Astruc, N Gonthier, C Mallet, L Landrieu - European Conference on …, 2024 - Springer
The diversity and complementarity of sensors available for Earth Observations (EO) calls for
develo** bespoke self-supervised multimodal learning approaches. However, current …

Optical remote sensing image understanding with weak supervision: Concepts, methods, and perspectives

J Yue, L Fang, P Ghamisi, W **e, J Li… - … and Remote Sensing …, 2022 - ieeexplore.ieee.org
In recent years, supervised learning has been widely used in various tasks of optical remote
sensing image (RSI) understanding, including RSI classification, pixel-wise segmentation …

There are no data like more data: Datasets for deep learning in earth observation

M Schmitt, SA Ahmadi, Y Xu, G Taşkin… - … and Remote Sensing …, 2023 - ieeexplore.ieee.org
Carefully curated and annotated datasets are the foundation of machine learning (ML), with
particularly data-hungry deep neural networks forming the core of what is often called …

GANmapper: geographical data translation

AN Wu, F Biljecki - International Journal of Geographical …, 2022 - Taylor & Francis
We present a new method to create spatial data using a generative adversarial network
(GAN). Our contribution uses coarse and widely available geospatial data to create maps of …

Autoregressive conditional neural processes

WP Bruinsma, S Markou, J Requiema… - arxiv preprint arxiv …, 2023 - arxiv.org
Conditional neural processes (CNPs; Garnelo et al., 2018a) are attractive meta-learning
models which produce well-calibrated predictions and are trainable via a simple maximum …