Published July 6, 2020 | Version v1
Conference paper Open

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

  • 1. CERTH-ITI

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.

Files

icme2020_preprint.pdf

Files (720.3 kB)

Name Size Download all
md5:471138a82e4b2891f5b6e1c2c5c0c9c7
720.3 kB Preview Download

Additional details

Funding

ReTV – Enhancing and Re-Purposing TV Content for Trans-Vector Engagement 780656
European Commission