A review of landcover classification with very-high resolution remotely sensed optical images—Analysis unit, model scalability and transferability
As an important application in remote sensing, landcover classification remains one of the
most challenging tasks in very-high-resolution (VHR) image analysis. As the rapidly …
most challenging tasks in very-high-resolution (VHR) image analysis. As the rapidly …
MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data
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 …
assessing its spectral behaviour via remote sensing, ultimately aiming at new operational …
Omnisat: Self-supervised modality fusion for earth observation
The diversity and complementarity of sensors available for Earth Observations (EO) calls for
develo** bespoke self-supervised multimodal learning approaches. However, current …
develo** bespoke self-supervised multimodal learning approaches. However, current …
Optical remote sensing image understanding with weak supervision: Concepts, methods, and perspectives
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 …
sensing image (RSI) understanding, including RSI classification, pixel-wise segmentation …
There are no data like more data: Datasets for deep learning in earth observation
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 …
particularly data-hungry deep neural networks forming the core of what is often called …
GANmapper: geographical data translation
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 …
(GAN). Our contribution uses coarse and widely available geospatial data to create maps of …
Autoregressive conditional neural processes
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 …
models which produce well-calibrated predictions and are trainable via a simple maximum …