Variational autoencoders (VAEs) are popular models for the generation of realistic images. Usually, the quality of generated images is estimated only by visual inspection, as the methods for the quantitative estimation are not fully developed. In this work, we present and test the methods that allow the possibility to evaluate the quality and the diversity of the images generated by a VAE objectively using an auxiliary classifier. The corresponding quality metrics are calculated for several implementations of VAE. The proposed metrics are especially valuable for the problems of preventing catastrophic forgetting during sequential learning. The experiments are performed on publicly available datasets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Quality metrics of variational autoencoders


    Beteiligte:


    Erscheinungsdatum :

    26.05.2020


    Format / Umfang :

    3029600 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Variational Autoencoders

    Ghojogh, Benyamin / Crowley, Mark / Karray, Fakhri et al. | Springer Verlag | 2022


    Deep Tracking Portfolios Using Autoencoders and Variational Autoencoders

    Urrego, Daniel Aragón / Nieto, Oscar Eduardo Reyes / Quimbayo, Carlos Andrés Zapata | Springer Verlag | 2024


    Certifiably Robust Variational Autoencoders

    Barrett, Ben / Camuto, Alexander / Willetts, Matthew et al. | ArXiv | 2021

    Freier Zugriff

    Mixed-curvature Variational Autoencoders

    Skopek, Ondrej / Ganea, Octavian-Eugen / Bécigneul, Gary | ArXiv | 2019

    Freier Zugriff