Geometry score: A method for comparing generative adversarial networks

Valentin Khrulkov, Ivan Oseledets

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    6 Citations (Scopus)

    Abstract

    One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse. In this work, we construct a novel measure of performance of a GAN by comparing geometrical properties of the underlying data manifold and the generated one, which provides both qualitative and quantitative means for evaluation. Our algorithm can be applied to datasets of an arbitrary nature and is not limited to visual data. We test the obtained metric on various real-life models and datasets and demonstrate that our method provides new insights into properties of GANs.

    Original languageEnglish
    Title of host publication35th International Conference on Machine Learning, ICML 2018
    EditorsJennifer Dy, Andreas Krause
    PublisherInternational Machine Learning Society (IMLS)
    Pages4114-4122
    Number of pages9
    ISBN (Electronic)9781510867963
    Publication statusPublished - 2018
    Event35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden
    Duration: 10 Jul 201815 Jul 2018

    Publication series

    Name35th International Conference on Machine Learning, ICML 2018
    Volume6

    Conference

    Conference35th International Conference on Machine Learning, ICML 2018
    Country/TerritorySweden
    CityStockholm
    Period10/07/1815/07/18

    Fingerprint

    Dive into the research topics of 'Geometry score: A method for comparing generative adversarial networks'. Together they form a unique fingerprint.

    Cite this