Conference paper Open Access

Fractional Step Discriminant Pruning: A Filter Pruning Framework for Deep Convolutional Neural Networks

Gkalelis, Nikolaos; Mezaris, Vasileios


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://zenodo.org/record/4244536</identifier>
  <creators>
    <creator>
      <creatorName>Gkalelis, Nikolaos</creatorName>
      <givenName>Nikolaos</givenName>
      <familyName>Gkalelis</familyName>
      <affiliation>CERTH-ITI</affiliation>
    </creator>
    <creator>
      <creatorName>Mezaris,  Vasileios</creatorName>
      <givenName>Vasileios</givenName>
      <familyName>Mezaris</familyName>
      <affiliation>CERTH-ITI</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Fractional Step Discriminant Pruning: A Filter Pruning Framework for Deep Convolutional Neural Networks</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>Deep convolutional neural networks</subject>
    <subject>asymptotic filter pruning</subject>
    <subject>class-separability criteria</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-07-06</date>
  </dates>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4244536</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1109/ICMEW46912.2020.9105979</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/retv-h2020</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;In this paper, a novel pruning framework is introduced to compress noisy or less discriminant filters in small fractional steps, in deep convolutional networks. The proposed framework utilizes a class-separability criterion that can exploit effectively the labeling information in annotated training sets. Additionally, an asymptotic schedule for the pruning rate and scaling factor is adopted so that the selected filters&amp;rsquo; weights collapse gradually to zero, providing improved robustness. Experimental results on the CIFAR-10, Google speech commands (GSC) and ImageNet32 (a downsampled version of ILSVRC-2012) show the efficacy of the proposed approach.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/780656/">780656</awardNumber>
      <awardTitle>Enhancing and Re-Purposing TV Content for Trans-Vector Engagement</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
259
45
views
downloads
Views 259
Downloads 45
Data volume 32.4 MB
Unique views 256
Unique downloads 45

Share

Cite as