activity
20162022
most citedBreaking the Limits of Message Passing Graph Neural Networks

28 citations · 28 across the 4 of their papers we have counts for

collaborators

6 papers

eess.IV2022

Effect of Prior-based Losses on Segmentation Performance: A Benchmark

Rosana El Jurdi, Caroline Petitjean, Veronika Cheplygina +2

Today, deep convolutional neural networks (CNNs) have demonstrated state-of-the-art performance for medical image segmentation, on various imaging modalities and tasks. Despite ear…

cs.LG202128 cited

Breaking the Limits of Message Passing Graph Neural Networks

Muhammet Balcilar, Pierre Héroux, Benoit Gaüzère +3

Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemen…

cs.CV2020

High-level Prior-based Loss Functions for Medical Image Segmentation: A Survey

Rosana El Jurdi, Caroline Petitjean, Paul Honeine +2

Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tas…

stat.ML2020

Statistical learning for sensor localization in wireless networks

Daniel Alshamaa, Farah Chehade, Paul Honeine

Indoor localization has become an important issue for wireless sensor networks. This paper presents a zoning-based localization technique that uses WiFi signals and works efficient…

cs.LG2020

Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks

Muhammet Balcilar, Guillaume Renton, Pierre Heroux +3

This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some e…

stat.AP2016

Bayesian Filtering of Smooth Signals: Application to Altimetry

Abderrahim Halimi, Gerald S. Buller, Steve McLaughlin +1

This paper presents a novel Bayesian strategy for the estimation of smooth signals corrupted by Gaussian noise. The method assumes a smooth evolution of a succession of continuous…