Conference paper Open Access

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

Gkalelis, Nikolaos; Mezaris, Vasileios

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.

Files (720.3 kB)
Name Size
icme2020_preprint.pdf
md5:471138a82e4b2891f5b6e1c2c5c0c9c7
720.3 kB Download
64
12
views
downloads
Views 64
Downloads 12
Data volume 8.6 MB
Unique views 64
Unique downloads 12

Share

Cite as