BriefGPT.xyz
Feb, 2019
GAN图像取证的泛化研究
On the generalization of GAN image forensics
HTML
PDF
Xinsheng Xuan, Bo Peng, Jing Dong, Wei Wang
TL;DR
本文研究使用预处理图像训练一种法医卷积神经网络模型，以提高对生成对抗网络图像的泛化能力，并证明所提出的方法的有效性。
Abstract
Recently the
gan
generated face images are more and more realistic with high-quality, even hard for human eyes to detect. On the other hand, the
forensics
community keeps on developing methods to detect these gen
→