MURAL - Maynooth University Research Archive Library

    Harmonic convolutional networks based on discrete cosine transform

    Ulicny, Matej and Krylov, Vladimir A. and Dahyot, Rozenn (2022) Harmonic convolutional networks based on discrete cosine transform. Pattern Recognition, 129 (108707). pp. 1-12. ISSN 00313203

    Download (2MB) | Preview

    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...

    Add this article to your Mendeley library


    Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. We propose to learn these filters as combinations of preset spectral filters defined by the Discrete Cosine Transform (DCT). Our proposed DCT-based harmonic blocks replace conventional convolutional layers to produce partially or fully harmonic versions of new or existing CNN architectures. Using DCT energy compaction properties, we demonstrate how the harmonic networks can be efficiently compressed by truncating high-frequency information in harmonic blocks thanks to the redundancies in the spectral domain. We report extensive experimental validation demonstrating benefits of the introduction of harmonic blocks into state-of-the-art CNN models in image classification, object detection and semantic segmentation applications.

    Item Type: Article
    Keywords: Harmonic network; Convolutional neural network; Discrete cosine transform; Image classification; Object detection; Semantic segmentation;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Faculty of Science and Engineering > Research Institutes > Hamilton Institute
    Item ID: 17749
    Identification Number:
    Depositing User: Rozenn Dahyot
    Date Deposited: 25 Oct 2023 14:33
    Journal or Publication Title: Pattern Recognition
    Publisher: Elsevier
    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