Conference paper Open Access

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

Gkalelis, Nikolaos; Mezaris, Vasileios


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Deep convolutional neural networks</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">asymptotic filter pruning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">class-separability criteria</subfield>
  </datafield>
  <controlfield tag="005">20201105002657.0</controlfield>
  <controlfield tag="001">4244536</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">July 2020.</subfield>
    <subfield code="g">MMC @ ICME 2020</subfield>
    <subfield code="a">Int. Workshop on Mobile Multimedia Computing (MMC2020) at the IEEE Int. Conf. on Multimedia and Expo (ICME)</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CERTH-ITI</subfield>
    <subfield code="a">Mezaris,  Vasileios</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">720286</subfield>
    <subfield code="z">md5:471138a82e4b2891f5b6e1c2c5c0c9c7</subfield>
    <subfield code="u">https://zenodo.org/record/4244536/files/icme2020_preprint.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-07-06</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-retv-h2020</subfield>
    <subfield code="o">oai:zenodo.org:4244536</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">CERTH-ITI</subfield>
    <subfield code="a">Gkalelis, Nikolaos</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Fractional Step Discriminant Pruning: A Filter Pruning Framework for Deep Convolutional Neural Networks</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-retv-h2020</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">780656</subfield>
    <subfield code="a">Enhancing and Re-Purposing TV Content for Trans-Vector Engagement</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1109/ICMEW46912.2020.9105979</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
260
45
views
downloads
Views 260
Downloads 45
Data volume 32.4 MB
Unique views 257
Unique downloads 45

Share

Cite as