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
Posted Content
Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions
Divya Saxena,Jiannong Cao +1 more
TL;DR: This study performs a comprehensive survey of the advancements in GANs design and optimization solutions and proposes a new taxonomy to structure solutions by key research issues and presents the promising research directions in this rapidly growing field.
Proceedings ArticleDOI
Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization
Mahfuzur Rahman Siddiquee,Zongwei Zhou,Nima Tajbakhsh,Ruibin Feng,Michael B. Gotway,Yoshua Bengio,Jianming Liang +6 more
TL;DR: Li et al. as discussed by the authors proposed a fixed-point GAN to identify a minimal subset of target pixels for domain translation, an ability that no GAN is equipped with yet, and trained by supervising same domain translation through a conditional identity loss, and regularizing cross-domain translation through revised adversarial, domain classification, and cycle consistency loss.
Posted Content
Unpaired Image Captioning via Scene Graph Alignments
TL;DR: Zhang et al. as mentioned in this paper proposed an unsupervised feature alignment method that maps the scene graph features from the image to the sentence modality, which can generate quite promising results without using any image-caption training pairs.
Posted Content
Detecting Bias with Generative Counterfactual Face Attribute Augmentation
TL;DR: A simple framework for identifying biases of a smiling attribute classifier is introduced and a set of metrics that measure the effect of manipulating a specific property of an image on the output of a trained classifier are introduced.
Journal ArticleDOI
Automatic epileptic EEG detection using convolutional neural network with improvements in time-domain
TL;DR: This paper proposes a novel automatic epileptic EEG detection method based on convolutional neural network (CNN) with two innovative improvements and treats this task as a big data classification issue.
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.