Domain shift caused by, e.g., different geographical regions or acquisit...
Crowdsourced platforms provide huge amounts of street-view images that
c...
Image classification is often prone to labelling uncertainty. To generat...
Discovering ancient agricultural terraces in desert regions is important...
Change detection (CD) by comparing two bi-temporal images is a crucial t...
Choosing how to encode a real-world problem as a machine learning task i...
Hyperspectral image (HSI) classification is gaining a lot of momentum in...
Disaster mapping is a critical task that often requires on-site experts ...
Localizing desired objects from remote sensing images is of great use in...
The Visual Question Answering (VQA) system offers a user-friendly interf...
Earth observation (EO) is a prime instrument for monitoring land and oce...
Multi-baseline interferometric synthetic aperture radar (InSAR) techniqu...
The use of language is innately political and often a vehicle of cultura...
Clouds and haze often occlude optical satellite images, hindering contin...
Aiming at answering questions based on the content of remotely sensed im...
The domain adaptation (DA) approaches available to date are usually not ...
In this paper, we introduce Planet-CR, a benchmark dataset for
high-reso...
Self-supervised pre-training bears potential to generate expressive
repr...
As unconventional sources of geo-information, massive imagery and text
m...
Automated crop-type classification using Sentinel-2 satellite time serie...
Earth observation, aiming at monitoring the state of planet Earth using
...
Unmanned aerial vehicles (UAVs) are widely applied for purposes of
inspe...
Unmanned aerial vehicles (UAVs) are now widely applied to data acquisiti...
High-resolution satellite images can provide abundant, detailed spatial
...
Hyperparameter optimization (HPO) is a well-studied research field. Howe...
Training semantic segmentation models with few annotated samples has gre...
In deep learning research, self-supervised learning (SSL) has received g...
Deep learning has proven to be a very effective approach for Hyperspectr...
We present and evaluate a weakly-supervised methodology to quantify the
...
The challenge of the cloud removal task can be alleviated with the aid o...
Technological and computational advances continuously drive forward the ...
Accurate and reliable building footprint maps are vital to urban plannin...
Visual question answering (VQA) for remote sensing scene has great poten...
Self-supervised learning (SSL) has attracted much interest in remote sen...
Obtaining a dynamic population distribution is key to many decision-maki...
Earth observation is a fundamental tool for monitoring the evolution of ...
Urban land use on a building instance level is crucial geo-information f...
With the rapid rise of neural architecture search, the ability to unders...
Generating 3D city models rapidly is crucial for many applications. Mono...
Building height retrieval from synthetic aperture radar (SAR) imagery is...
Algorithmic design in neural architecture search (NAS) has received a lo...
Neural architecture search is a promising area of research dedicated to
...
Although Convolution Neural Networks (CNNs) has made substantial progres...
Lots of effort in neural architecture search (NAS) research has been
ded...
Humanitarian mapping from space with machine learning helps policy-maker...
Many current deep learning approaches make extensive use of backbone net...
Due to their increasing spread, confidence in neural network predictions...
Clouds are a very important factor in the availability of optical remote...
Aerial scene recognition is a fundamental visual task and has attracted ...
In the last years we have witnessed the fields of geosciences and remote...