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
Image Inpainting Based on Generative Adversarial Networks
TL;DR: The proposed model can deal with large-scale missing pixels and generate realistic completion results and uses the skip-connection in the generator to improve the prediction power of the model.
Journal ArticleDOI
Fetal Congenital Heart Disease Echocardiogram Screening Based on DGACNN: Adversarial One-Class Classification Combined with Video Transfer Learning
Yuxin Gong,Zhang Yingying,Haogang Zhu,Jing Lv,Qian Cheng,Hongjia Zhang,Yihua He,Shuliang Wang +7 more
TL;DR: The proposed DGACNN network has high potential for helping cardiologists complete early FHD screenings and outperforms other state-of-the-art networks by 1%–20% in recognizing FHD.
Book ChapterDOI
NAM: Non-Adversarial Unsupervised Domain Mapping
Yedid Hoshen,Lior Wolf +1 more
TL;DR: This work introduces an alternative method: Non-Adversarial Mapping (NAM), which separates the task of target domain generative modeling from the cross-domain mapping task, and relies on a pre-trained generative model of the target domain, and aligns each source image with an image synthesized from the targetdomain, while jointly optimizing the domain mapping function.
Posted Content
Realistic River Image Synthesis using Deep Generative Adversarial Networks
TL;DR: A generative adversarial network (GAN) model capable of generating high-resolution and realistic river images that can be used to support models in surface water estimation, river meandering, wetland loss and other hydrological research studies is proposed.
Posted Content
Manifold Mixup: Learning Better Representations by Interpolating Hidden States
Vikas Verma,Alex Lamb,Christopher Beckham,Amir Najafi,Aaron Courville,Ioannis Mitliagkas,Yoshua Bengio +6 more
TL;DR: Manifold Mixup achieves large improvements over strong baselines in supervised learning, robustness to single-step adversarial attacks, semi-supervised learning, and Negative Log-Likelihood on held out samples.
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.