MURAL - Maynooth University Research Archive Library

    Harmonic Networks with Limited Training Samples

    Ulicny, Matej and Krylov, Vladimir A and Dahyot, Rozenn (2019) Harmonic Networks with Limited Training Samples. 2019 27th European Signal Processing Conference (EUSIPCO). pp. 1-5. ISSN 2076-1465

    Download (406kB) | Preview

    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...

    Add this article to your Mendeley library


    Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.

    Item Type: Article
    Keywords: Lapped Discrete Cosine Transform; harmonic network; convolutional filter; limited data;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Item ID: 15158
    Identification Number:
    Depositing User: Rozenn Dahyot
    Date Deposited: 20 Dec 2021 12:59
    Journal or Publication Title: 2019 27th European Signal Processing Conference (EUSIPCO)
    Publisher: IEEE
    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