For a decade now, convolutional deep neural networks have demonstrated their ability to produce excellent results for computer vision. For this, these models transform the input image into a series of latent representations. In this thesis, we work on improving the "quality'' of the latent representations of ConvNets for different tasks. First, we work on regularizing those representations to increase their robustness toward intra-class variations and thus improve their performance for classification. To do so, we develop a loss based on information theory metrics to decrease the entropy conditionally to the class. Then, we propose to structure the information in two complementary latent spaces, solving a conflict between the invariance of ...
We leverage probabilistic models of neural representations to investigate how residual networks fit ...
Deep learning has become a pervasive tool in the field of machine learning, delivering unprecedented...
Recent advancements in the areas of deep learning and visual information processing have presented a...
I first review the existing methods based on regularization for continual learning. While regularizi...
Transfer learning with deep convolutional neural networks significantly reduces the computation and ...
The increased availability of large amounts of data, from images in social networks, speech waveform...
Data symmetries have been used to successfully learn robust and optimal representation either via au...
In this thesis, we examine some practical difficulties of deep learning models.Indeed, despite the p...
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space i...
Malgré des progrès spectaculaires en vision par ordinateur au cours de la dernière décennie, les rés...
Deep neural networks are representation learning techniques. During training, a deep net is capable ...
Deep neural networks have achieved impressive results in many image classification tasks. However, s...
It is common to compare properties of visual information processing by artificial neural networks an...
International audienceIt is widely believed that the success of deep convolutional networks is based...
Image representation is a key component in visual recognition systems. In visual recognition problem...
We leverage probabilistic models of neural representations to investigate how residual networks fit ...
Deep learning has become a pervasive tool in the field of machine learning, delivering unprecedented...
Recent advancements in the areas of deep learning and visual information processing have presented a...
I first review the existing methods based on regularization for continual learning. While regularizi...
Transfer learning with deep convolutional neural networks significantly reduces the computation and ...
The increased availability of large amounts of data, from images in social networks, speech waveform...
Data symmetries have been used to successfully learn robust and optimal representation either via au...
In this thesis, we examine some practical difficulties of deep learning models.Indeed, despite the p...
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space i...
Malgré des progrès spectaculaires en vision par ordinateur au cours de la dernière décennie, les rés...
Deep neural networks are representation learning techniques. During training, a deep net is capable ...
Deep neural networks have achieved impressive results in many image classification tasks. However, s...
It is common to compare properties of visual information processing by artificial neural networks an...
International audienceIt is widely believed that the success of deep convolutional networks is based...
Image representation is a key component in visual recognition systems. In visual recognition problem...
We leverage probabilistic models of neural representations to investigate how residual networks fit ...
Deep learning has become a pervasive tool in the field of machine learning, delivering unprecedented...
Recent advancements in the areas of deep learning and visual information processing have presented a...