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
Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
TL;DR: Asymmetrically-relaxed distribution alignment is proposed, a new approach that overcomes some limitations of standard domain-adversarial algorithms and characterize precise assumptions under which the algorithm is theoretically principled and demonstrate empirical benefits on both synthetic and real datasets.
Journal ArticleDOI
Unsupervised MR-to-CT Synthesis Using Structure-Constrained CycleGAN
TL;DR: This paper proposes a structure-constrained cycleGAN for unsupervised MR-to-CT synthesis by defining an extra structure-consistency loss based on the modality independent neighborhood descriptor and utilizes a spectral normalization technique to stabilize the training process and a self-attention module to model the long-range spatial dependencies in the synthetic images.
Proceedings ArticleDOI
MineGAN: Effective Knowledge Transfer From GANs to Target Domains With Few Images
Yaxing Wang,Abel Gonzalez-Garcia,David Berga,Luis Herranz,Fahad Shahbaz Khan,Joost van de Weijer +5 more
TL;DR: MineGAN as discussed by the authors uses a miner network to identify which part of the generative distribution of each pretrained GAN outputs closest to the target domain, which steers GAN sampling towards suitable regions of the latent space, which avoids pathologies of other methods such as mode collapse and lack of flexibility.
Proceedings ArticleDOI
RiFeGAN: Rich Feature Generation for Text-to-Image Synthesis From Prior Knowledge
TL;DR: A novel rich feature generating text-to-image synthesis, called RiFeGAN, to enrich the given description and exploits multi-captions attentional generative adversarial networks to synthesize images from those features.
Journal ArticleDOI
Data augmentation for enhancing EEG-based emotion recognition with deep generative models
TL;DR: The experimental results demonstrate that the proposed data augmentation methods based on generative models outperform the existingData augmentation approaches such as conditional VAE, Gaussian noise, and rotational data augmented.
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.