Capsule Networks are an alternative to the conventional CNN structure for object recognition. They replace max pooling with a dynamic routing of capsule activation. The goal is to better exploit the spatial relationships of the learned features, not only to increase recognition performance, but also improve generalization capability and sample-efficiency. Recently, two algorithms for dynamic routing of capsules have been proposed. Although they received a lot of interest and they are from the same group, an experimental comparison of both is still missing. In this work we compare these two routing algorithms and provide experimental results on data efficiency and generalization to increased input images. Although the experiments are limited to variants of the MNIST dataset, they indicate that the approach of Sabour et al. (2017) is better at learning from few training samples and the EM routing of Hinton et al. (2018) is better at generalizing to changed image sizes.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Comparison of Data Efficiency in Dynamic Routing for Capsule Networks



    Erscheinungsdatum :

    2018-01-01


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    004 / 629



    An experimental comparison of dynamic routing protocols in mobile networks

    Vadim, Glazunov / Oleg, Gusikhin / Leonid, Kurochkin et al. | IEEE | 2014


    VEHICLE CAPSULE NETWORKS

    ZHAO ZHEN / UNNIKRISHNAN KP / KLEINHANS ASHLEY NAOMI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Vehicle capsule networks

    ZHAO ZHEN / KLEINHANS ASHLEY NAOMI / PATEL ISHAN et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    VEHICLE CAPSULE NETWORKS

    ZHAO ZHEN / UNNIKRISHNAN KP / KLEINHANS ASHLEY NAOMI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    DYNAMIC V2X NETWORKS AND VEHICLE ROUTING

    ROSALES RAFAEL / GEISSLER FLORIAN / PAULITSCH MICHAEL et al. | Europäisches Patentamt | 2022

    Freier Zugriff