VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we would like to take into account at generation time. We propose in this paper GLSR-VAE, a Geodesic Latent Space Regularization for the Variational AutoEncoder architecture and its generalizations which allows a fine control on the embedding of the data into the latent space. When augmenting the VAE loss with this regularization, changes in the learned latent space reflects changes of the attributes of the data. This deeper understanding of the VAE latent space structure offers the possibility to modulate the attributes of the generated data in a continuous way. We demonstrate its efficiency on a monophonic music generation task where we manage to generate variations of discrete sequences in an intended and playful way.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures


    Beteiligte:
    Hadjeres, Gaetan (Autor:in) / Nielsen, Frank (Autor:in) / Pachet, Francois (Autor:in)


    Erscheinungsdatum :

    01.11.2017


    Format / Umfang :

    744503 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    GLSR-VAE: Geodesic Latent Space Regularization for Variational AutoEncoder Architectures

    Hadjeres, Gaëtan / Nielsen, Frank / Pachet, François | ArXiv | 2017

    Freier Zugriff

    Variational Autoencoder-Based Vehicle Trajectory Prediction with an Interpretable Latent Space

    Neumeier, Marion / Betsch, Michael / Tollkuhn, Andreas et al. | IEEE | 2021


    Variational Autoencoder

    Pinheiro Cinelli, Lucas / Araújo Marins, Matheus / Barros da Silva, Eduardo Antúnio et al. | Springer Verlag | 2021


    Variational Autoencoder

    Okadome, Takeshi | Springer Verlag | 2025


    Segment-Based Credit Scoring Using Latent Clusters in the Variational Autoencoder

    Mancisidor, Rogelio Andrade / Kampffmeyer, Michael / Aas, Kjersti et al. | ArXiv | 2018

    Freier Zugriff