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
Proceedings ArticleDOI
360-Degree Textures of People in Clothing from a Single Image
TL;DR: In this article, the authors infer texture and geometry in the UV-space of the SMPL model using an image-to-image translation method, which can be applied to the model in order to naturally generalize to novel poses, shapes and even new clothing.
Journal ArticleDOI
PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting
Weiwei Cai,Zhanguo Wei +1 more
TL;DR: PiiGAN as mentioned in this paper proposes a new style extractor which can extract the style feature (latent vector) from the ground truth, and then the extracted style feature and the ground-truth are both input into the generator.
Posted Content
A U-Net Based Discriminator for Generative Adversarial Networks.
TL;DR: The novel discriminator improves over the state of the art in terms of the standard distribution and image quality metrics, enabling the generator to synthesize images with varying structure, appearance and levels of detail, maintaining global and local realism.
Proceedings ArticleDOI
HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
TL;DR: HashGAN is presented, a novel architecture for deep learning to hash, which learns compact binary hash codes from both real images and diverse images synthesized by generative models, conditioned on the pairwise similarity information.
Proceedings ArticleDOI
RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion
TL;DR: In this paper, RL-GAN-Net is applied to point cloud shape completion that converts noisy, partial point cloud data into a high-fidelity completed shape by controlling the GAN.
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.