Open AccessProceedings Article
Improved training of wasserstein GANs
Ishaan Gulrajani,Faruk Ahmed,Martin Arjovsky,Vincent Dumoulin,Aaron Courville +4 more
- Vol. 30, pp 5769-5779
TLDR
The authors proposed to penalize the norm of the gradient of the critic with respect to its input to improve the training stability of Wasserstein GANs and achieve stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.Abstract:
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 poor 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 with continuous generators. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms.read more
Citations
More filters
Proceedings ArticleDOI
Attribute Manipulation Generative Adversarial Networks for Fashion Images
TL;DR: Attribute Manipulation Generative Adversarial Networks (AMGAN) for fashion images outperforms state-of-the-art methods using traditional evaluation metrics as well as an alternative one that is based on image retrieval.
Proceedings ArticleDOI
EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation.
TL;DR: A multi-resolution adversarial model – EmpDG is proposed, to generate more empathetic responses and an interactive adversarial learning framework which exploits the user feedback, to identify whether the generated responses evoke emotion perceptivity in dialogues.
Book ChapterDOI
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
TL;DR: A model-agnostic, unbiased stochastic approximation of this term based on Hutchinson's estimator to compute it efficiently during training and provides empirical evidence that the Hessian Penalty encourages substantial shrinkage when applied to over-parameterized latent spaces.
Journal ArticleDOI
Generative Adversarial Networks-Based Data Augmentation for Brain–Computer Interface
TL;DR: This study shows that using GANs for EEG augmentation can significantly improve BCI performance, especially in real-life applications, whereby users' attention may be diverted.
Posted Content
Discriminator Rejection Sampling.
TL;DR: A rejection sampling scheme using the discriminator of a GAN to approximately correct errors in the GAN generator distribution and a practical algorithm - called Discriminator Rejection Sampling (DRS) - that can be used on real data-sets is designed.
References
More filters
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
Journal ArticleDOI
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
TL;DR: This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units that are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement in both immediate-reinforcement tasks and certain limited forms of delayed-reInforcement tasks, and they do this without explicitly computing gradient estimates.
Posted Content
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TL;DR: This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.
Posted Content
Improved Techniques for Training GANs
TL;DR: In this article, the authors present a variety of new architectural features and training procedures that apply to the generative adversarial networks (GANs) framework and achieve state-of-the-art results in semi-supervised classification on MNIST, CIFAR-10 and SVHN.
Proceedings Article
Categorical Reparameterization with Gumbel-Softmax
Eric Jang,Shixiang Gu,Ben Poole +2 more
TL;DR: Gumbel-Softmax as mentioned in this paper replaces the non-differentiable samples from a categorical distribution with a differentiable sample from a novel Gumbel softmax distribution, which has the essential property that it can be smoothly annealed into the categorical distributions.