BARLAUD , Michel

This paper deals with supervised classification and feature selection with application in the context of high dimensional features. A classical approach leads to an optimization problem minimizing the within sum of squares in the clusters (2 norm) with an 1 penalty in order to promote sparsity. It has been known for decades that 1 norm is more...

This paper deals with supervised discriminative and generative modeling. Classical methods are based on variational autoencoders or supervised variational autoencoders encourage the latent space to fit a prior distribution, like a Gaussian. However, they tend to make stronger assumptions on the data, often leading to higher asymptotic bias when...

International audience

Deep neural networks (DNN) have been applied recently to different domains andperform better than classical state-of-the-art methods. However the high level of performances of DNNs is most often obtained with networks containing millions of parameters and for which training requires substantial computational power. To deal with this...

Nous proposons dans ce papier d'étudier les métriques de similarité entre images dans le cadre des problèmes inverses tels que la déconvolution et la séparation de sources. La métrique de similarité que nous proposons est basée sur les notions de théorie de l'information (distance de Kullback-Leibler) et est combinée avec une transformée en...

no abstract

International audience

Nearest Neighbor (NN) search is a crucial tool that remains critical in many challenging applications of computational geometry (e.g., surface reconstruction, clustering) and computer vision (e.g., image and information retrieval, classification, data mining). We present an effective Bregman ball tree [5] (Bb-tree) construction algorithm that...

no abstract

National audience

International audience

no abstract

Nearest Neighbor (NN) retrieval is a crucial tool of many computer vision tasks. Since the brute-force naive search is too time consuming for most applications, several tailored data structures have been proposed to improve the efficiency of NN search. Among these, vantage point tree (vp-tree) was introduced for information retrieval in metric...

In this paper, we study the effect of different regularizers and their implications in high dimensional image classification and sparse linear unmixing. Although kernelization or sparse methods are globally accepted solutions for processing data in high dimensions, we present here a study on the impact of the form of regularization used and its...

National audience

no abstract

This paper deals with region-of-interest (ROI) tracking in video sequences. The goal is to determine in successive frames the region which best matches, in terms of a similarity measure, an ROI defined in a reference frame. Two aspects of a similarity measure between a reference region and a candidate region can be distinguished: radiometry...

International audience

no abstract

no abstract

This paper deals with region-of-interest (ROI) tracking in video sequences. The goal is to determine in successive frames the region which best matches, in terms of a similarity measure, a ROI defined in a reference frame. Some tracking methods define similarity measures which efficiently combine several visual features into a probability...

International audience

International audience

no abstract

The recent improvements of graphics processing units (GPU) offer to the computer vision community a powerful processing platform. Indeed, a lot of highly-parallelizable computer vision problems can be significantly accelerated using GPU architecture. Among these algorithms, the k nearest neighbor search (KNN) is a well-known problem linked with...