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
Journal ArticleDOI
Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
TL;DR: In this article, a recurrent, stochastic super-resolution GAN is proposed to generate ensembles of time-evolving high-resolution atmospheric fields for an input consisting of a low-resolution sequence of images of the same field.
Proceedings ArticleDOI
Adversarial Colorization of Icons Based on Contour and Color Conditions
TL;DR: A dual conditional generative adversarial network (GAN) is trained to help designers create icons that are widely used in banners, signboards, billboards, homepages, and mobile apps and is able to colorize icons demanded by designers and greatly reduces their workload.
Journal ArticleDOI
SAR Target Recognition Based on Cross-Domain and Cross-Task Transfer Learning
Ke Wang,Gong Zhang,Henry Leung +2 more
TL;DR: This paper introduces simulated SAR data to alleviate the problem of insufficient training data and proposes a model that integrates meta-learning and adversarial domain adaptation, which effectively solves the cross-domain and cross-task transfer problem.
Proceedings Article
Ae-ot: a new generative model based on extended semi-discrete optimal transport
TL;DR: This work gives a theoretic explanation of the mode collapse or mode mixture problems by Figalli’s regularity theory of optimal transportation maps, and proposes a AE-OT model that effectively prevents mode collapse and mode mixture.
Posted Content
Lipschitz regularity of deep neural networks: analysis and efficient estimation
Kevin Scaman,Aladin Virmaux +1 more
TL;DR: This paper provides AutoLip, the first generic algorithm for upper bounding the Lipschitz constant of any automatically differentiable function, and proposes an improved algorithm named SeqLip that takes advantage of the linear computation graph to split the computation per pair of consecutive layers.
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.