Une véritable approche L0 pour l'apprentissage de dictionnaire - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Une véritable approche L0 pour l'apprentissage de dictionnaire

Yuan Liu
  • Fonction : Auteur
Stéphane Canu
Paul Honeine
Su Ruan

Résumé

Sparse representation learning has recently gained a great success in signal and image processing, thanks to recent advances in dictionary learning. To this end, the L0-norm is often used to control the sparsity level. Nevertheless, optimization problems based on the L0-norm are non-convex and NP-hard. For these reasons, relaxation techniques have been attracting much attention of researchers, by priorly targeting approximation solutions (e.g. L1-norm, pursuit strategies). On the contrary, this paper considers the exact L0-norm optimization problem and proves that it can be solved effectively, despite of its complexity. The proposed method reformulates the problem as a Mixed-Integer Quadratic Program (MIQP) and gets the global optimal solution by applying existing optimization software. Because the main difficulty of this approach is its computational time, two techniques are introduced that improve the computational speed. Finally, our method is applied to image denoising which shows its feasibility and relevance compared to the state-of-the-art.
Fichier principal
Vignette du fichier
17.gretsi.dictionnaire.pdf (246.39 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01965912 , version 1 (27-12-2018)

Identifiants

  • HAL Id : hal-01965912 , version 1

Citer

Yuan Liu, Stéphane Canu, Paul Honeine, Su Ruan. Une véritable approche L0 pour l'apprentissage de dictionnaire. Actes du 26-ème Colloque GRETSI sur le Traitement du Signal et des Images, 2017, Juan-Les-Pins, France. ⟨hal-01965912⟩
34 Consultations
26 Téléchargements

Partager

Gmail Facebook X LinkedIn More