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:Â
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
Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification
TL;DR: A virtual label called Multi-pseudo Regularized Label (MpRL) is proposed and assigned to generated data to train a deep neural network in a semi-supervised learning fashion and outperforms state-of-the-art methods.
Journal ArticleDOI
Knowledge mapping-based adversarial domain adaptation: A novel fault diagnosis method with high generalizability under variable working conditions
TL;DR: A knowledge mapping-based adversarial domain adaptation (KMADA) method with a discriminator and a feature extractor to generalize knowledge from target to source domain and indicates the irreplaceable superiority of the KMADA, which achieves the highest diagnosis accuracy.
Proceedings ArticleDOI
NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding
TL;DR: Zhang et al. as mentioned in this paper proposed to directly keep track of the negative triplets with cache, which can improve the performance of negative sampling in KG embeddings by avoiding the vanishing gradient problem.
Journal ArticleDOI
Enforcing statistical constraints in generative adversarial networks for modeling chaotic dynamical systems
TL;DR: In this article, a statistical constrained generative adversarial network (GAN) was proposed to solve the Rayleigh-Benard convection, a turbulent flow system that is an idealized model of the Earth's atmosphere.
Proceedings ArticleDOI
Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation
Giorgos Bouritsas,Sergiy Bokhnyak,Stylianos Ploumpis,Stefanos Zafeiriou,Michael M. Bronstein +4 more
TL;DR: In this article, a graph convolutional operator is proposed to enforce consistent local orderings of the vertices of the graph, through the spiral operator, thus breaking the permutation invariance property that is adopted by all the prior work on Graph Neural Networks.
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.