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
Episode-Based Prototype Generating Network for Zero-Shot Learning
TL;DR: A novel generative model is proposed that synthesizes visual prototypes conditioned on the class semantic prototypes into an adversarial framework paired with a parameter-economic Multi-modal Cross-Entropy Loss to capture the discriminative information.
Book ChapterDOI
Dual Adversarial Network: Toward Real-World Noise Removal and Noise Generation
TL;DR: Zhang et al. as mentioned in this paper proposed a unified framework to simultaneously deal with the real-world image noise removal and noise generation tasks, which learns the joint distribution of the clean-noisy image pairs.
Posted Content
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Kundan Kumar,Rithesh Kumar,Thibault de Boissiere,Lucas Gestin,Wei Zhen Teoh,Jose Sotelo,Alexandre de Brebisson,Yoshua Bengio,Aaron Courville +8 more
TL;DR: This article proposed a non-autoregressive, fully convolutional GAN for mel-spectrogram inversion and achieved state-of-the-art performance in speech synthesis, music domain translation and unconditional music synthesis.
Proceedings ArticleDOI
Conditional Channel Gated Networks for Task-Aware Continual Learning
Davide Abati,Jakub M. Tomczak,Tijmen Blankevoort,Simone Calderara,Rita Cucchiara,Babak Ehteshami Bejnordi +5 more
TL;DR: In this article, task-specific gating modules are used to select which filters to apply on the given input, ensuring no loss in the performance of the model for previously learned tasks.
Proceedings ArticleDOI
Adversarial Feature Hallucination Networks for Few-Shot Learning
TL;DR: In this article, two novel regularizers, i.e., the classification regularizer and the anti-collapse regularizer, are incorporated into AFHN to encourage discriminability and diversity of the synthesized features, respectively.
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.