MURAL - Maynooth University Research Archive Library

    Using WGAN for Improving Imbalanced Classification Performance

    Bhatia, Snehal and Dahyot, Rozenn (2019) Using WGAN for Improving Imbalanced Classification Performance. CEUR Workshop Proceedings, 2563. pp. 365-375. ISSN 1613-0073

    Download (1MB) | Preview

    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...

    Add this article to your Mendeley library


    This paper investigates data synthesis with a Generative Adversarial Network (GAN) for augmenting the amount of data used for training classifiers (in supervised learning) to compensate for class imbalance (when the classes are not represented equally by the same number of training samples). Our data synthesis approach with GAN is compared with data augmentation in the context of image classification. Our experimental results show encouraging results in comparison to standard data augmentation schemes based on image transforms.

    Item Type: Article
    Keywords: WGAN; Improving; Imbalanced; Classification; Performance;
    Academic Unit: Faculty of Science and Engineering > Research Institutes > Hamilton Institute
    Item ID: 15250
    Depositing User: Rozenn Dahyot
    Date Deposited: 17 Jan 2022 12:48
    Journal or Publication Title: CEUR Workshop Proceedings
    Publisher: CEUR
    Refereed: Yes
    Use Licence: This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

    Repository Staff Only(login required)

    View Item Item control page


    Downloads per month over past year

    Origin of downloads