非线性卷积网络的高效准确近似

Nov, 2014

Efficient and Accurate Approximations of Nonlinear Convolutional Networks

Xiangyu Zhang, Jianhua Zou, Xiang Ming, Kaiming He, Jian Sun

TL;DR本文旨在加速深度卷积神经网络的测试时间计算，通过最小化非线性响应的重建误差，附加一种低秩约束，以帮助降低过滤器的复杂度，该算法可以减小多层输入的叠加误差并提高模型精度，可将ImageNet的训练速度提升4倍，精度提高4.7%。

Abstract

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method tak