BriefGPT.xyz
Dec, 2021
使用超调制将无条件 GAN 转化为有条件 GAN
Hyper-GAN: Transferring Unconditional to Conditional GANs with HyperNetworks
HTML
PDF
Héctor Laria, Yaxing Wang, Joost van de Weijer, Bogdan Raducanu
TL;DR
本论文旨在通过构建超调制生成网络，利用先前训练好的非泛化GANs来实现对条件GANs的迁移学习，提高训练的效率和样本利用率，并运用对比学习进一步提高判别器的性能。
Abstract
Conditional
gans
have matured in recent years and are able to generate high-quality realistic images. However, the computational resources and the training data required for the training of high-quality
gans
are
→