JOUFFROY, Emma; GIREMUS, Audrey; BERTHOUMIEU, Yannick; BACH, Olivier; HUGGET, Alain

doi:10.23919/EUSIPCO55093.2022.9909746

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

JOUFFROY, Emma
Laboratoire de l'intégration, du matériau au système [IMS]

GIREMUS, Audrey

Laboratoire de l'intégration, du matériau au système [IMS]

BERTHOUMIEU, Yannick
Laboratoire de l'intégration, du matériau au système [IMS]

Langue

Communication dans un congrès

Ce document a été publié dans

2022 30th European Signal Processing Conference (EUSIPCO), 2022 30th European Signal Processing Conference (EUSIPCO), 2022-08-29, Belgrade. 2022-10-18p. 1407-1411

Résumé en anglais

Variational auto-encoders (VAEs) are powerful generative neural networks based on latent variables. They aim to capture the distribution of a dataset, by building an informative space composed of a reduced number of variables. However, the size of this latent space is both sensitive and difficult to adjust. Thus, most state-of-the-art architectures experience either dis-entanglement issues, or, at the opposite, posterior collapse. Both phenomena impair the interpretability of the latent variables. In this paper, we propose a variant of the VAE which is able to automatically determine the informative components of the latent space. It consists in augmenting the vanilla VAE with auxiliary variables and defining a hierarchical model which favors that only a subset of the latent variables are used for the encoding. We refer to it as NGVAE. We compare its performance with other auto-encoder based architectures.< Réduire

Mots clés

Architecture

Neural networks

Buildings

Europe

Signal processing

Encoding

Neural net architecture

Deep neural networks

Variational inference

Generative models

Unsupervised models

Métadonnées

Partager cette publication !

Licence d’utilisation du document

Automatic selection of latent variables in variational auto-encoders

Langue

Ce document a été publié dans

Résumé en anglais

Mots clés

URI

DOI

Unités de recherche