Open AccessPosted Content
GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium
Martin Heusel,Hubert Ramsauer,Thomas Unterthiner,Bernhard Nessler,Günter Klambauer,Sepp Hochreiter +5 more
TL;DR: In this article, a two time-scale update rule (TTUR) was proposed for training GANs with stochastic gradient descent on arbitrary GAN loss functions, which has an individual learning rate for both the discriminator and the generator.
read more
Abstract: Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved. We propose a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions. TTUR has an individual learning rate for both the discriminator and the generator. Using the theory of stochastic approximation, we prove that the TTUR converges under mild assumptions to a stationary local Nash equilibrium. The convergence carries over to the popular Adam optimization, for which we prove that it follows the dynamics of a heavy ball with friction and thus prefers flat minima in the objective landscape. For the evaluation of the performance of GANs at image generation, we introduce the "Frechet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score. In experiments, TTUR improves learning for DCGANs and Improved Wasserstein GANs (WGAN-GP) outperforming conventional GAN training on CelebA, CIFAR-10, SVHN, LSUN Bedrooms, and the One Billion Word Benchmark.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
StyleGAN2 Distillation for Feed-Forward Image Manipulation
Yuri Viazovetskyi,Vladimir Ivashkin,Evgeny Kashin +2 more
- 23 Aug 2020
TL;DR: It is shown that the quality of generation using the proposed pipeline is comparable to StyleGAN2 backpropagation and current state-of-the-art methods in these particular tasks, and the resulting pipeline is an alternative to existing GANs, trained on unpaired data.
123
Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination
Jae Woong Soh,Gu Yong Park,Junho Jo,Nam Ik Cho +3 more
- 15 Jun 2019
TL;DR: Zhang et al. as mentioned in this paper proposed a domain prior to constrain the output image in the natural manifold, which eventually generates more natural and realistic images. But the generated fake details often make undesirable artifacts and the overall image looks somewhat unnatural.
•Posted Content
Towards Automatic Threat Detection: A Survey of Advances of Deep Learning within X-ray Security Imaging
Samet Akcay,Toby P. Breckon +1 more
TL;DR: This paper aims to review computerised X-ray security imaging algorithms by taxonomising the field into conventional machine learning and contemporary deep learning applications, with a particular focus on object classification, detection, segmentation and anomaly detection tasks.
SpaText: Spatio-Textual Representation for Controllable Image Generation
Omri Avrahami,Thomas Hayes,Oran Gafni,Sonal Gupta,Yaniv Taigman,Devi Parikh,Dani Lischinski,Ohad Fried,Xiaoyue Yin +8 more
TL;DR: SpaText as discussed by the authors is a new method for text-to-image generation using open-vocabulary scene control, where the user provides a segmentation map where each region of interest is annotated by a free-form natural language description.
122
ForkGAN: Seeing into the Rainy Night
Ziqiang Zheng,Yang Wu,Xinran Han,Jianbo Shi +3 more
- 23 Aug 2020
TL;DR: A ForkGAN for task-agnostic image translation that can boost multiple vision tasks in adverse weather conditions with a fork-shape generator with one encoder and two decoders that disentangles the domain-specific and domain-invariant information.
122
References
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
•Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
- 06 Jul 2015
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.