In the last few years, deep learning has changed irrevocably the field of computer vision. Faster, giving better results, and requiring a lower degree of expertise to use than traditional computer vision methods, deep learning has become ubiquitous in every imaging application. This includes medical imaging applications. At the beginning of this thesis, there was still a strong lack of tools and understanding of how to build efficient neural networks for specific tasks. Thus this thesis first focused on the topic of hyper-parameter optimization for deep neural networks, i.e. methods for automatically finding efficient neural networks on specific tasks. The thesis includes a comparison of different methods, a performance improvement of one o...
RÉSUMÉ: La sclérose en plaques est la maladie auto-immune la plus courante du système nerveux centra...
We are seven billion humans with unique cortical folding patterns. The cortical folding process occu...
Inference and optimization algorithms usually have hyperparameters that require to be tuned in order...
Non-invasive Brain Computer Interfaces (BCIs) allow a user to control a machine using only their bra...
Les réseaux de neurones profonds ont démontré un fort impact dans de nombreuses applications du mond...
The problems of continuous optimization are numerous, in economics, in signal processing, in neural ...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
This thesis focuses on non-linear image reconstruction methods applied to super-resolution in micros...
In this thesis we propose the use of mid-level representations, and in particular i) medial axes, ii...
Physically based deformable models have become ubiquitous in computer graphics. It allow to syntheti...
Ces dernières années, l'intelligence artificielle a été considérablement avancée et l'apprentissage ...
This dissertation is a summary of a line of research, that I wasactively involved in, on learning in...
The goal of this thesis is to develop models, representations and structured learning algorithms for...
Detecting and following the main objects of a video is necessary to describe its content in order to...
We propose a participatory science outreach approach allowing us to co-construct with our audiences ...
RÉSUMÉ: La sclérose en plaques est la maladie auto-immune la plus courante du système nerveux centra...
We are seven billion humans with unique cortical folding patterns. The cortical folding process occu...
Inference and optimization algorithms usually have hyperparameters that require to be tuned in order...
Non-invasive Brain Computer Interfaces (BCIs) allow a user to control a machine using only their bra...
Les réseaux de neurones profonds ont démontré un fort impact dans de nombreuses applications du mond...
The problems of continuous optimization are numerous, in economics, in signal processing, in neural ...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
This thesis focuses on non-linear image reconstruction methods applied to super-resolution in micros...
In this thesis we propose the use of mid-level representations, and in particular i) medial axes, ii...
Physically based deformable models have become ubiquitous in computer graphics. It allow to syntheti...
Ces dernières années, l'intelligence artificielle a été considérablement avancée et l'apprentissage ...
This dissertation is a summary of a line of research, that I wasactively involved in, on learning in...
The goal of this thesis is to develop models, representations and structured learning algorithms for...
Detecting and following the main objects of a video is necessary to describe its content in order to...
We propose a participatory science outreach approach allowing us to co-construct with our audiences ...
RÉSUMÉ: La sclérose en plaques est la maladie auto-immune la plus courante du système nerveux centra...
We are seven billion humans with unique cortical folding patterns. The cortical folding process occu...
Inference and optimization algorithms usually have hyperparameters that require to be tuned in order...