Automated multi-stage compression of neural networks

Julia Gusak, Maksym Kholiavchenko, Evgeny Ponomarev, Larisa Markeeva, Philip Blagoveschensky, Andrzej Cichocki, Ivan Oseledets

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

    14 Citations (Scopus)

    Abstract

    Low-rank tensor approximations are very promising for compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our approach improves the compression rate while maintaining the accuracy for a variety of tasks.

    Original languageEnglish
    Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages2501-2508
    Number of pages8
    ISBN (Electronic)9781728150239
    DOIs
    Publication statusPublished - Oct 2019
    Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
    Duration: 27 Oct 201928 Oct 2019

    Publication series

    NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

    Conference

    Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
    Country/TerritoryKorea, Republic of
    CitySeoul
    Period27/10/1928/10/19

    Keywords

    • Automated
    • Iterative
    • Low rank approximation
    • Model compression
    • Neural networks

    Fingerprint

    Dive into the research topics of 'Automated multi-stage compression of neural networks'. Together they form a unique fingerprint.

    Cite this