Conference paper Open Access

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

Gkalelis, Nikolaos; Mezaris, Vasileios


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Gkalelis, Nikolaos</dc:creator>
  <dc:creator>Mezaris,  Vasileios</dc:creator>
  <dc:date>2020-07-06</dc:date>
  <dc:description>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’ 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.</dc:description>
  <dc:identifier>https://zenodo.org/record/4244536</dc:identifier>
  <dc:identifier>10.1109/ICMEW46912.2020.9105979</dc:identifier>
  <dc:identifier>oai:zenodo.org:4244536</dc:identifier>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/780656/</dc:relation>
  <dc:relation>url:https://zenodo.org/communities/retv-h2020</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:subject>Deep convolutional neural networks</dc:subject>
  <dc:subject>asymptotic filter pruning</dc:subject>
  <dc:subject>class-separability criteria</dc:subject>
  <dc:title>Fractional Step Discriminant Pruning: A Filter Pruning Framework for Deep Convolutional Neural Networks</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>
257
44
views
downloads
Views 257
Downloads 44
Data volume 31.7 MB
Unique views 254
Unique downloads 44

Share

Cite as