• Login
    View Item 
    •   Eurographics DL Home
    • Eurographics Partner Events
    • VMV: Vision, Modeling, and Visualization
    • VMV19
    • View Item
    •   Eurographics DL Home
    • Eurographics Partner Events
    • VMV: Vision, Modeling, and Visualization
    • VMV19
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Stochastic Convolutional Sparse Coding

    Thumbnail
    View/Open
    047-054.pdf (3.035Mb)
    paper_1010_supplement.pdf (2.176Mb)
    Date
    2019
    Author
    Xiong, Jinhui ORCID
    Richtarik, Peter ORCID
    Heidrich, Wolfgang ORCID
    Pay-Per-View via TIB Hannover:

    Try if this item/paper is available.

    Metadata
    Show full item record
    Abstract
    State-of-the-art methods for Convolutional Sparse Coding usually employ Fourier-domain solvers in order to speed up the convolution operators. However, this approach is not without shortcomings. For example, Fourier-domain representations implicitly assume circular boundary conditions and make it hard to fully exploit the sparsity of the problem as well as the small spatial support of the filters. In this work, we propose a novel stochastic spatial-domain solver, in which a randomized subsampling strategy is introduced during the learning sparse codes. Afterwards, we extend the proposed strategy in conjunction with online learning, scaling the CSC model up to very large sample sizes. In both cases, we show experimentally that the proposed subsampling strategy, with a reasonable selection of the subsampling rate, outperforms the state-of-the-art frequency-domain solvers in terms of execution time without losing the learning quality. Finally, we evaluate the effectiveness of the over-complete dictionary learned from large-scale datasets, which demonstrates an improved sparse representation of the natural images on account of more abundant learned image features.
    BibTeX
    @inproceedings {10.2312:vmv.20191317,
    booktitle = {Vision, Modeling and Visualization},
    editor = {Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael},
    title = {{Stochastic Convolutional Sparse Coding}},
    author = {Xiong, Jinhui and Richtarik, Peter and Heidrich, Wolfgang },
    year = {2019},
    publisher = {The Eurographics Association},
    ISBN = {978-3-03868-098-7},
    DOI = {10.2312/vmv.20191317}
    }
    URI
    https://doi.org/10.2312/vmv.20191317
    https://diglib.eg.org:443/handle/10.2312/vmv20191317
    Collections
    • VMV19

    Eurographics Association copyright © 2013 - 2022 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA
     

     

    Browse

    All of Eurographics DLCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    BibTeX | TOC

    Create BibTeX Create Table of Contents

    Eurographics Association copyright © 2013 - 2022 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA