Auxiliary Guided Autoregressive Variational Autoencoders

Thomas Lucas 1 Jakob Verbeek 1
1 Thoth - Apprentissage de modèles à partir de données massives
LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
Abstract : Generative modeling of high-dimensional data is a key problem in machine learn- ing. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local image statistics respectively, suggest hybrid models combining the strengths of both models. Our contribution is to train such hybrid models using an auxiliary loss function that controls which information is captured by the latent variables and what is left to the autoregressive decoder. In contrast, prior work on such hy- brid models needed to limit the capacity of the autoregressive decoder to prevent degenerate models that ignore the latent variables and only rely on autoregressive modeling. Our approach results in models with meaningful latent variable repre- sentations, and which rely on powerful autoregressive decoders to model image details. Our model generates qualitatively convincing samples, and yields state- of-the-art quantitative results.
Document type :
Conference papers
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-01652881
Contributor : Thomas Lucas <>
Submitted on : Thursday, November 30, 2017 - 6:32:50 PM
Last modification on : Friday, January 25, 2019 - 10:38:01 AM

File

paper_iclr.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01652881, version 1

Collections

Citation

Thomas Lucas, Jakob Verbeek. Auxiliary Guided Autoregressive Variational Autoencoders. ECML-PKDD 2018, Sep 2018, Dublin, Ireland. ⟨hal-01652881v1⟩

Share

Metrics

Record views

425

Files downloads

184