1.9k citations
- Georges Kaddoum5 profiles30 · h 49
- Ismail Ben Ayed3 profiles30 · h 52
- P. Giard28 · h 18
- R. Sabourin28 · h 58
- J. Dolz26 · h 43
- Christian Desrosiers2 profiles24 · h 37
- Eric Granger2 profiles20 · h 32
- F. Gagnon17 · h 32
- Rafael M. O. Cruz17 · h 22
- M. Cheriet15 · h 51
- C. Thibeault14 · h 21
- Marco Pedersoli3 profiles14 · h 20
- Université du Québec à MontréalCA58 papers
- McGill UniversityCA38 papers
- Polytechnique MontréalCA25 papers
- Universidade Federal de PernambucoBR17 papers
- Université du QuébecCA14 papers
- Université de MontréalCA13 papers
- Centre National de la Recherche ScientifiqueFR11 papers
- University of OttawaCA11 papers
- Guilin University of Electronic TechnologyCN10 papers
- Concordia UniversityCA9 papers
- École Polytechnique Fédérale de LausanneCH9 papers
- Carleton UniversityCA8 papers
14 papers · 2 filters
Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis
Karthik Gopinath, Christian Desrosiers, Herve Lombaert
Brain surface analysis is essential to neuroscience, however, the complex geometry of the brain cortex hinders computational methods for this task. The difficulty arises from a dis…
Adversarial Learning of General Transformations for Data Augmentation
Saypraseuth Mounsaveng, David Vazquez, Ismail Ben Ayed +1
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heur…
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
Jérôme Rony, Soufiane Belharbi, Jose Dolz +3
Using deep learning models to diagnose cancer from histology data presents several challenges. Cancer grading and localization of regions of interest (ROIs) in these images normall…
Revisiting CycleGAN for semi-supervised segmentation
Arnab Kumar Mondal, Aniket Agarwal, Jose Dolz +1
In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotat…
Self-supervised blur detection from synthetically blurred scenes
Aitor Alvarez-Gila, Adrian Galdran, Estibaliz Garrote +1
Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred…
Discretely-constrained deep network for weakly supervised segmentation
Jizong Peng, Hoel Kervadec, Jose Dolz +3
An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such cons…