Paul Honeine

3 papers · 2021–2021 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICLR (1) ICML (1) MIDL (1)

Top co-authors

Pierre Héroux (2) Muhammet Balcilar (2) Benoit Gaüzère (2) Sébastien Adam (2) Veronika Cheplygina (1) Rosana EL Jurdi (1) Guillaume Renton (1) Pascal Vasseur (1) Caroline Petitjean (1) Fahed Abdallah (1)

Research topics

Deep Learning (2) Machine Learning (2) Architectures (2) Computer Vision (1) Core Methods (1) Domain-Specific (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1) Processing (1)

Keywords

graph convolution (2) graph neural network (2) weisfeiler-lehman test (2) spectral analysis (1) expressive power (1) convolutional network (1) graph isomorphism (1) spectral domain (1) organ segmentation (1) semantic segmentation (1) boundary loss (1) medical image segmentation (1) message passing (1)

Papers

Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective ICLR 2021 A Surprisingly Effective Perimeter-based Loss for Medical Image Segmentation MIDL 2021 Breaking the Limits of Message Passing Graph Neural Networks ICML 2021