BriefGPT.xyz
Jul, 2023
卷积神经网络训练中的数据增强:对图像注入噪声
Data Augmentation in Training CNNs: Injecting Noise to Images
HTML
PDF
M. Eren Akbiyik
TL;DR
本研究分析了不同噪声模型及其强度对卷积神经网络的影响,通过结构相似度(SSIM)度量给出相同大小的噪声模型来进行比较,提出了一些新的启发式策略和建议,可以优化图像分类的最优学习过程。
Abstract
noise injection
is a fundamental tool for
data augmentation
, and yet there is no widely accepted procedure to incorporate it with learning frameworks. This study analyzes the effects of adding or applying differe
→