BriefGPT.xyz
Nov, 2018
通过增量规则化进行高效卷积神经网络的结构化剪枝
Structured Pruning for Efficient ConvNets via Incremental Regularization
HTML
PDF
Huan Wang, Qiming Zhang, Yuehai Wang, Haoji Hu
TL;DR
提出了一种逐步分配不同正则化因子的新型正则化剪枝方法(称为IncReg),可在不影响CNN性能的情况下消除冗余参数,有效性通过与最先进的方法相比较后在流行的CNN上得到证明。
Abstract
parameter pruning
is a promising approach for
cnn compression
and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based <
→