Generative Adversarial Networks (GANs) are powerful generative models, but
suffer from training instability. The recently proposed Wasserstein GAN (WGAN)
makes progress toward stable training of GANs, but sometimes can still generate
only low-quality samples or fail to converge. We find that these problems are
often due to the use of weight clipping in WGAN to enforce a Lipschitz
constraint on the critic, which can lead to undesired behavior. We propose an
alternative to clipping weights: penalize the norm of gradient of the critic
with respect to its input. Our proposed method performs better than standard
WGAN and enables stable training of a wide variety of GAN architectures with
almost no hyperparameter tuning, including 101-layer ResNets and language
models over discrete data. We also achieve high quality generations on CIFAR-10
and LSUN bedrooms.

提出了一种比传统的 WGAN 更好的 GAN 训练方法，使用正则化替代权重截取，通过惩罚评判器对其输入梯度的范数，可以实现各种 GAN 结构的稳定训练和高质量生成。

改进的 Wasserstein GANs 训练

Improved Training of Wasserstein GANs

In this paper, we propose a generative model, Temporal Generative Adversarial
Nets (TGAN), which can learn a semantic representation of unlabeled videos, and
is capable of generating videos. Unlike existing Generative Adversarial Nets
(GAN)-based methods that generate videos with a single generator consisting of
3D deconvolutional layers, our model exploits two different types of
generators: a temporal generator and an image generator. The temporal generator
takes a single latent variable as input and outputs a set of latent variables,
each of which corresponds to an image frame in a video. The image generator
transforms a set of such latent variables into a video. To deal with
instability in training of GAN with such advanced networks, we adopt a recently
proposed model, Wasserstein GAN, and propose a novel method to train it stably
in an end-to-end manner. The experimental results demonstrate the effectiveness
of our methods.

本文提出了一种生成式模型 Temporal Generative Adversarial Nets（TGAN），用于学习未标记视频的语义表示，并能够生成视频。我们的模型利用两种不同类型的生成器：时间生成器和图像生成器，解决了利用现有的基于 GAN 的方法生成视频时存在的问题。为了稳定训练，我们采用了最近提出的 Wasserstein GAN 模型，并提出了一种稳定的端到端训练方法。实验结果表明了我们方法的有效性。