MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

ICCV 2019 Zechun LiuHaoyuan MuXiangyu ZhangZichao GuoXin YangTim Kwang-Ting ChengJian Sun

In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.