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
The Devil is in the Decoder: Classification, Regression and GANs
Zbigniew Wojna,Vittorio Ferrari,Sergio Guadarrama,Nathan Silberman,Liang-Chieh Chen,Alireza Fathi,Jasper Uijlings +6 more
TL;DR: This paper presents an extensive comparison of a variety of decoders for a range of pixel-wise tasks ranging from classification, regression to synthesis and introduces new residual-like connections for decoder.
Journal ArticleDOI
Robust stochastic optimal dispatching method of multi-energy virtual power plant considering multiple uncertainties
TL;DR: The proposed robust stochastic optimal dispatching method can get the scheduling scheme with the lowest operating cost in the worst scenario and is conducive to reducing the overall scheduling cost of the system.
Posted Content
Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection
TL;DR: This work introduces an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain, and hence detect abnormality based on deviation from this model.
Proceedings ArticleDOI
AdversarialNAS: Adversarial Neural Architecture Search for GANs
TL;DR: The AdversarialNAS is the first method that can search the architectures of generator and discriminator simultaneously in a differentiable manner and only takes 1 GPU day to search for a superior generative model in the proposed large search space.
Proceedings ArticleDOI
SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
TL;DR: A Suppression of Background Shift Generative Adversarial Network (SBSGAN) is proposed to generate images with suppressed backgrounds and achieves competitive performance on three re-ID datasets, i.e., Market-1501, DukeMTMC-reID, and CUHK03.
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.