244 citations · 711 across the 19 of their papers we have counts for
4 papers · 1 filter
Directional Graph Networks
Dominique Beaini, Saro Passaro, Vincent Létourneau +3
The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this lim…
Principal Neighbourhood Aggregation for Graph Nets
Gabriele Corso, Luca Cavalleri, Dominique Beaini +2
Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on is…
Improving Convolutional Neural Networks Via Conservative Field Regularisation and Integration
Dominique Beaini, Sofiane Achiche, Maxime Raison
Current research in convolutional neural networks (CNN) focuses mainly on changing the architecture of the networks, optimizing the hyper-parameters and improving the gradient desc…
Saliency Enhancement using Gradient Domain Edges Merging
Dominique Beaini, Sofiane Achiche, Alexandre Duperre +1
In recent years, there has been a rapid progress in solving the binary problems in computer vision, such as edge detection which finds the boundaries of an image and salient object…