Conference paper Open Access

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

Gkalelis, Nikolaos; Mezaris, Vasileios


Citation Style Language JSON Export

{
  "DOI": "10.1109/ICMEW46912.2020.9105979", 
  "author": [
    {
      "family": "Gkalelis, Nikolaos"
    }, 
    {
      "family": "Mezaris,  Vasileios"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2020, 
        7, 
        6
      ]
    ]
  }, 
  "abstract": "<p>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&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.</p>", 
  "title": "Fractional Step Discriminant Pruning: A Filter Pruning Framework for Deep Convolutional Neural Networks", 
  "id": "4244536", 
  "type": "paper-conference", 
  "event": "Int. Workshop on Mobile Multimedia Computing (MMC2020) at the IEEE Int. Conf. on Multimedia and Expo (ICME) (MMC @ ICME 2020)"
}
260
45
views
downloads
Views 260
Downloads 45
Data volume 32.4 MB
Unique views 257
Unique downloads 45

Share

Cite as