125 citations
- Centre National de la Recherche ScientifiqueFR28 papers
- Université Jean MonnetFR21 papers
- Lyon 1 UniversitéFR15 papers
- Leading Health CareSE9 papers
- Institut d’Optique Graduate SchoolFR6 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR5 papers
- Institut de Planétologie et d'Astrophysique de GrenobleFR5 papers
- CEA DAM Île-de-FranceFR4 papers
- Centre de Recherche Astrophysique de LyonFR4 papers
- L'Alliance BoviteqCA4 papers
- Université de RennesFR4 papers
- Université Grenoble AlpesFR4 papers
6 papers · 1 filter
Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100 speed-up
Shibin Parameswaran, Charles-Alban Deledalle, Loïc Denis +1
Image restoration methods aim to recover the underlying clean image from corrupted observations. The Expected Patch Log-likelihood (EPLL) algorithm is a powerful image restoration…
Integrating Context of Statements within Description Logics
Antoine Zimmermann, José M. Giménez-García
We address the problem of providing contextual information about a logical formula (eg provenance, date of validity, or confidence) and representing it within a logical system. In…
A simple expression for the map of Asplund's distances with the multiplicative Logarithmic Image Processing (LIP) law
Guillaume Noyel, Michel Jourlin
We introduce a simple expression for the map of Asplund's distances with the multiplicative Logarithmic Image Processing (LIP) law. It is a difference between a morphological dilat…
Automatic Classification of Bright Retinal Lesions via Deep Network Features
Ibrahim Sadek, Mohamed Elawady, Abd El Rahman Shabayek
The diabetic retinopathy is timely diagonalized through color eye fundus images by experienced ophthalmologists, in order to recognize potential retinal features and identify early…
Residual Conv-Deconv Grid Network for Semantic Segmentation
Damien Fourure, Rémi Emonet, Elisa Fromont +3
This paper presents GridNet, a new Convolutional Neural Network (CNN) architecture for semantic image segmentation (full scene labelling). Classical neural networks are implemented…
Improving Max-Sum through Decimation to Solve Loopy Distributed Constraint Optimization Problems
Jesús Cerquides, Rémi Emonet, Gauthier Picard +1
In the context of solving large distributed constraint optimization problems (DCOP), belief-propagation and approximate inference algorithms are candidates of choice. However, in g…