Search Results for author:
Found 10 papers, 0 papers with code
Evolution of urban areas and land surface temperature
With the global population on the rise, our cities have been expanding to accommodate the growing number of people.
Exploring Self-Attention for Crop-type Classification Explainability
Using explainable machine learning to reveal the inner workings of these models is an important step towards improving stakeholders' trust and efficient agriculture monitoring.
Prototypical Variational Autoencoders
Variational autoencoders are unsupervised generative models that implement latent space regularization towards a known distribution, enabling stochastic synthesis from straightforward sampling procedures.
Controlling Weather Field Synthesis Using Variational Autoencoders
One of the consequences of climate change is anobserved increase in the frequency of extreme cli-mate events.
Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data
This work proposes a multi-task fully convolutional architecture for tree species mapping in dense forests from sparse and scarce polygon-level annotations using hyperspectral UAV-borne data.
Decoupling Shape and Density for Liver Lesion Synthesis Using Conditional Generative Adversarial Networks
Lesion synthesis received much attention with the rise of efficient generative models for augmenting training data, drawing lesion evolution scenarios, or aiding expert training.
Ground Roll Suppression using Convolutional Neural Networks
Seismic data processing plays a major role in seismic exploration as it conditions much of the seismic interpretation performance.
Implanting Synthetic Lesions for Improving Liver Lesion Segmentation in CT Exams
The success of supervised lesion segmentation algorithms using Computed Tomography (CT) exams depends significantly on the quantity and variability of samples available for training.
An argument in favor of strong scaling for deep neural networks with small datasets
We evaluated our approach with up to 32 GPUs and show that weak scaling not only does not have the same accuracy as the sequential model, it also fails to converge most of time.
Automatic tracking of vessel-like structures from a single starting point
Further visual results also show the potential of our approach for identifying vascular networks topologies.
