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 learning. 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 hybrid 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 representations, 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 [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01652881
Contributor : Thomas Lucas <>
Submitted on : Thursday, July 19, 2018 - 4:36:30 PM
Last modification on : Wednesday, March 20, 2019 - 1:29:03 AM

File

paper_ecml.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Thomas Lucas, Jakob Verbeek. Auxiliary Guided Autoregressive Variational Autoencoders. ECML-PKDD 2018 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2018, Dublin, Ireland. pp.443-458, ⟨10.1007/978-3-030-10925-7_27⟩. ⟨hal-01652881v2⟩

Share

Metrics

Record views

625

Files downloads

470