BriefGPT.xyz
Jun, 2019
卷积神经网络上数据增强的进一步优势
Further advantages of data augmentation on convolutional neural networks
HTML
PDF
Alex Hernández-García, Peter König
TL;DR
本文研究数据增强在卷积神经网络中的隐式规则效应,与显式正则化技术(如权重衰减和Dropout)相比,数据增强能更易于适应不同的网络结构和训练数据。通过对不同网络架构和训练数据量的消融研究,我们揭示了数据增强的优势,这是长期被忽视的问题。
Abstract
data augmentation
is a popular technique largely used to enhance the training of
convolutional neural networks
. Although many of its benefits are well known by deep learning researchers and practitioners, its imp
→