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
Posted Content
Generative adversarial networks and adversarial methods in biomedical image analysis.
TL;DR: An introduction to GANs and adversarial methods is provided, with an overview of biomedical image analysis tasks that have benefited from such methods, and potential future research directions are proposed.
Posted Content
Labeled Graph Generative Adversarial Networks.
Shuangfei Fan,Bert Huang +1 more
TL;DR: This work proposes labeled-graph generative adversarial networks (LGGAN) to train deep generative models for graph-structured data with node labels and test the approach on various types of graph datasets, such as collections of citation networks and protein graphs.
Posted Content
Unsupervised Wasserstein Distance Guided Domain Adaptation for 3D Multi-Domain Liver Segmentation
TL;DR: This work presents an approach based on the Wasserstein distance guided disentangled representation to achieve 3D multi-domain liver segmentation and introduces a content discriminator to further facilitate the representation disentanglement.
Book ChapterDOI
Consistent Brain Ageing Synthesis
TL;DR: In this article, the authors adopt adversarial training to learn the joint distribution of brain images and ages, and simulate aged images by a network conditioned on age (a continuous variable) encoded as an ordinal embedding vector.
Posted Content
CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator.
TL;DR: This work proposes a novel method of generating high-quality Chinese calligraphy characters over state-of-the-art methods measured through numerical evaluations and human subject studies by incorporating Chinese characters' component information into its model.
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.