对称卷积滤波器：约束CNN参数的一种新方法
计算机视觉与模式识别
2022-03-01 v1
摘要
我们提出了一种基于对称滤波器约束CNN参数的新技术。我们研究了在不同对称性组合下对最先进网络的影响。我们证明我们的模型提供了有效的泛化能力以及对参数冗余的结构化消除。最后我们通过将我们的方法与其他剪枝技术进行比较作结。
引用
@article{arxiv.2202.13099,
title = {Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN},
author = {Harish Agrawal and Sumana T. and S. K. Nandy},
journal= {arXiv preprint arXiv:2202.13099},
year = {2022}
}
备注
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