Multi-view Generative Adversarial Networks

Abstract : 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.
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02101339
Contributor : Mickael Chen <>
Submitted on : Tuesday, April 16, 2019 - 4:10:17 PM
Last modification on : Friday, July 5, 2019 - 3:26:03 PM

File

ECML_PKDD___Multi_view_Generat...
Files produced by the author(s)

Identifiers

Citation

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⟩

Share

Metrics

Record views

36

Files downloads

21