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
Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection
TL;DR: Li et al. as discussed by the authors presented Defect-GAN, an automated defect synthesis network that generates realistic and diverse defect samples for training accurate and robust defect inspection networks, which employs a novel compositional layer-based architecture for generating realistic defects within various image backgrounds with different textures and appearances.
Journal Article
Few-shot Adaptation of Generative Adversarial Networks
TL;DR: This paper proposes a simple and effective method, Few-Shot GAN (FSGAN), for adapting GANs in few-shot settings (less than 100 images), which repurposes component analysis techniques and learns to adapt the singular values of the pre-trained weights while freezing the corresponding singular vectors.
Journal ArticleDOI
AI-assisted superresolution cosmological simulations.
TL;DR: A deep neural network is built to enhance low-resolution dark-matter simulations, generating superresolution realizations that agree remarkably well with authentic high-resolution counterparts on their statistical properties and are orders-of-magnitude faster.
Journal ArticleDOI
Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
TL;DR: In this paper, a temporally self-supervised adversarial learning is proposed to achieve temporally coherent solutions without sacrificing spatial detail for video super-resolution and unpaired video translation.
Posted Content
Exposing GAN-synthesized Faces Using Landmark Locations.
TL;DR: In this paper, the location of facial landmark points is used to expose GAN-synthesized images using the locations of the facial landmarks, which is based on the observation that the facial parts configuration generated by GAN models are different from those of the real faces.
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.