Convolutional Neural Network Pruning Using Filter Attenuation

02/09/2020
by   Morteza Mousa Pasandi, et al.
0

Filters are the essential elements in convolutional neural networks (CNNs). Filters are corresponded to the feature maps and form the main part of the computational and memory requirement for the CNN processing. In filter pruning methods, a filter with all of its components, including channels and connections, are removed. The removal of a filter can cause a drastic change in the network's performance. Also, the removed filters cannot come back to the network structure. We want to address these problems in this paper. We propose a CNN pruning method based on filter attenuation in which weak filters are not directly removed. Instead, weak filters are attenuated and gradually removed. In the proposed attenuation approach, weak filters are not abruptly removed, and there is a chance for these filters to return to the network. The filter attenuation method is assessed using the VGG model for the Cifar10 image classification task. Simulation results show that the filter attenuation works with different pruning criteria, and better results are obtained in comparison with the conventional pruning methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/05/2023

Efficient CNNs via Passive Filter Pruning

Convolutional neural networks (CNNs) have shown state-of-the-art perform...
research
11/18/2018

RePr: Improved Training of Convolutional Filters

A well-trained Convolutional Neural Network can easily be pruned without...
research
10/29/2018

Demystifying Neural Network Filter Pruning

Based on filter magnitude ranking (e.g. L1 norm), conventional filter pr...
research
05/21/2020

Feature Statistics Guided Efficient Filter Pruning

Building compact convolutional neural networks (CNNs) with reliable perf...
research
03/05/2020

Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications

Even though the Convolutional Neural Networks (CNN) has shown superior r...
research
12/07/2018

Removal of Parameter Adjustment of Frangi Filters in Case of Coronary Angiograms

Frangi Filters are one of the widely used filters for enhancing vessels ...
research
01/22/2020

Pruning CNN's with linear filter ensembles

Despite the promising results of convolutional neural networks (CNNs), a...

Please sign up or login with your details

Forgot password? Click here to reset