利用冗余特征剪枝构建高效ConvNets

Feb, 2018

利用冗余特征剪枝构建高效ConvNets

Building Efficient ConvNets using Redundant Feature Pruning

Babajide O. Ayinde, Jacek M. Zurada

TL;DR该论文提出了一种通过消除冗余特征（或滤波器）来修剪深度和/或宽度卷积神经网络模型的高效技术，其依据特征空间中的相对余弦距离区分它们和它们的连接特征映射并优化精度和推理性能，但优化后的算法能将VGG-16的推理成本降低40％、ResNet-56的推理成本降低27％、ResNet-110的推理成本减少39％。

Abstract

This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network