Picture for S. K. Nandy

S. K. Nandy

Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN

Add code
Feb 26, 2022
Harish Agrawal, Sumana T., S. K. Nandy
Figure 1 for Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN
Figure 2 for Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN
Figure 3 for Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN
Figure 4 for Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN

We propose a novel technique to constrain parameters in CNN based on symmetric filters. We investigate the impact on SOTA networks when varying the combinations of symmetricity. We demonstrate that our models offer effective generalisation and a structured elimination of redundancy in parameters. We conclude by comparing our method with other pruning techniques.

* Copyright 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon