Multi-view Generative Adversarial Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Multi-view Generative Adversarial Networks

Résumé

Learning over multi-view data is a challenging problem with strong practical applications. Most related studies focus on the classification point of view and assume that all the views are available at any time. We consider an extension of this framework in two directions. First, based on the BiGAN model, the Multi-view BiGAN (MV-BiGAN) is able to perform density estimation from multi-view inputs. Second, it can deal with missing views and is able to update its prediction when additional views are provided. We illustrate these properties on a set of experiments over different datasets.
Fichier principal
Vignette du fichier
ECML_PKDD___Multi_view_Generative_Adversarial_Networks_.pdf (946.07 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02101339 , version 1 (16-04-2019)

Identifiants

Citer

Mickaël Chen, Ludovic Denoyer. Multi-view Generative Adversarial Networks. ECML PKDD 2017, Sep 2017, Skopje, Macedonia. pp.175-188, ⟨10.1007/978-3-319-71246-8_11⟩. ⟨hal-02101339⟩
83 Consultations
100 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More