Refining activation downsampling with SoftPool

Alexandros Stergiou, Ronald Poppe, Grigorios Kalliatakis

    Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

    257 Citations (Scopus)

    Abstract

    Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of the pooling operation is the minimization of information loss, with respect to the initial activation maps, without a significant impact on the computation and memory overhead. To meet these requirements, we propose SoftPool: a fast and efficient method for exponentially weighted activation downsampling. Through experiments across a range of architectures and pooling methods, we demonstrate that SoftPool can retain more information in the reduced activation maps. This refined downsampling leads to improvements in a CNN's classification accuracy. Experiments with pooling layer substitutions on ImageNet1K show an increase in accuracy over both original architectures and other pooling methods. We also test SoftPool on video datasets for action recognition. Again, through the direct replacement of pooling layers, we observe consistent performance improvements while computational loads and memory requirements remain limited.

    Original languageEnglish
    Title of host publicationProceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
    PublisherInstitute of Electrical and Electronics Engineers (IEEE)
    Pages10337-10346
    Number of pages10
    ISBN (Electronic)9781665428125
    DOIs
    Publication statusPublished - 28 Feb 2022
    Event18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 - Virtual, Online, Canada
    Duration: 11 Oct 202117 Oct 2021

    Publication series

    NameProceedings of the IEEE International Conference on Computer Vision
    ISSN (Print)1550-5499
    ISSN (Electronic)2380-7504

    Conference

    Conference18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
    Country/TerritoryCanada
    CityVirtual, Online
    Period11/10/2117/10/21

    Bibliographical note

    Publisher Copyright:
    © 2021 IEEE

    Fingerprint

    Dive into the research topics of 'Refining activation downsampling with SoftPool'. Together they form a unique fingerprint.

    Cite this