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
A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation.
Paolo Andreini,Simone Bonechi,Monica Bianchini,Alessandro Mecocci,Franco Scarselli,Andrea Sodi +5 more
TL;DR: The adoption of a two-stage process simplifies the generation task, so that the network training requires fewer images with consequent lower memory usage, and with only a handful of training samples, the approach generates realistic high-resolution images, which can be successfully used to enlarge small available datasets.
Journal ArticleDOI
Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention
TL;DR: This work constrain the problem with the assumption that the translated image needs to be perceptually similar to the original image and also appears to be drawn from the new domain, and proposes a simple yet effective image translation model consisting of a single generator trained with a self-regularization term and an adversarial term.
Journal ArticleDOI
DDGC: Generative Deep Dexterous Grasping in Clutter
TL;DR: DDGC as discussed by the authors is a fast generative multi-finger grasp sampling method that can generate high quality grasps in cluttered scenes from a single RGB-D image, which is built as a network that encodes scene information to produce coarse-to-fine collision-free grasp poses and configurations.
Journal ArticleDOI
Generative adversarial framework for depth filling via Wasserstein metric, cosine transform and domain transfer
TL;DR: The issue of depth filling is addressed using a self-supervised feature learning model that predicts missing depth pixel values based on the context and structure of the scene and trained in an adversarial fashion to complete scene depth.
Journal ArticleDOI
Breaking medical data sharing boundaries by using synthesized radiographs.
Tianyu Han,Sven Nebelung,Christoph Haarburger,Nicolas Horst,Sebastian Reinartz,Dorit Merhof,Dorit Merhof,Fabian Kiessling,Fabian Kiessling,Volkmar Schulz,Volkmar Schulz,Daniel Truhn +11 more
TL;DR: This work proposes to use generative models (GMs) to produce high-resolution synthetic radiographs that do not contain any personal identification information, and integrates federated learning strategies to improve the performance of CV algorithms trained on smaller datasets.
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.