BriefGPT.xyz
Dec, 2014
限定时间成本下的卷积神经网络
Convolutional Neural Networks at Constrained Time Cost
HTML
PDF
Kaiming He, Jian Sun
TL;DR
本文研究在时间约束成本下，卷积神经网络的准确性和架构设计所需的权衡。通过一系列对比实验，得出一个在ImageNet数据集中准确率很高（11.8%的top-5误差，10视图测试），但比AlexNet（16.0%的top-5误差，10视图测试）快20%的网络架构。
Abstract
Though recent advanced
convolutional neural networks
(CNNs) have been improving the image recognition
accuracy
, the models are getting more complex and time-consuming. For real-world applications in industrial an
→