论文标题
不平衡的gan：使用变异自动编码器预先培训生成对抗网络的生成器
Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
论文作者
论文摘要
我们提出了不平衡的gan，它可以使用变异自动编码器（VAE）预先培训生成对抗网络（GAN）的生成器。我们通过防止早期歧视者的更快收敛来确保对发电机进行稳定的训练。此外，我们在早期时代的发生器和鉴别器之间取得平衡，从而维持对gan的稳定训练。我们将不平衡的gan应用于众所周知的公共数据集，发现不平衡的gans减少模式崩溃。我们还表明，在早期时代的稳定学习，更快的收敛性和更好的图像质量方面，不平衡的gans的表现要优于普通剂量。
We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE). We guarantee the stable training of the generator by preventing the faster convergence of the discriminator at early epochs. Furthermore, we balance between the generator and the discriminator at early epochs and thus maintain the stabilized training of GANs. We apply Unbalanced GANs to well known public datasets and find that Unbalanced GANs reduce mode collapses. We also show that Unbalanced GANs outperform ordinary GANs in terms of stabilized learning, faster convergence and better image quality at early epochs.
