Unrolled Generative Adversarial Networks, NIPS 2016 | Luke Metz, Google Brain
Luke Metz, Ben Poole, David Pfau, Jascha Sohl-Dickstein
https://arxiv.org/abs/1611.02163
NIPS 2016 Workshop on Adversarial Training Spotlight
We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of the data distribution by the generator.
Видео Unrolled Generative Adversarial Networks, NIPS 2016 | Luke Metz, Google Brain канала Preserve Knowledge
https://arxiv.org/abs/1611.02163
NIPS 2016 Workshop on Adversarial Training Spotlight
We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of the data distribution by the generator.
Видео Unrolled Generative Adversarial Networks, NIPS 2016 | Luke Metz, Google Brain канала Preserve Knowledge
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Tutorial on Generative adversarial networks - Domain Adversarial Learning
Generative Adversarial Networks (GANs) - Computerphile
Fixing GAN optimization through competitive gradient descent - Anima Anandkumar
257 - Exploring GAN latent space to generate images with desired features
Semantic Segmentation using Adversarial Networks, NIPS 2016 | Pauline Luc, Facebook AI Research
Conditional Image Synthesis with Auxiliary Classifier GANs, NIPS 2016 | Augustus Odena, Google Brain
Understand the Math and Theory of GANs in ~ 10 minutes
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization, NIPS 2016
David Duvenaud | Reflecting on Neural ODEs | NeurIPS 2019
NIPS 2016 Workshop on Adversarial Training - Soumith Chintala - How to train a GAN
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
How to train a GAN, NIPS 2016 | Soumith Chintala, Facebook AI Research
Editing Faces using Artificial Intelligence
A Friendly Introduction to Generative Adversarial Networks (GANs)
Self-Supervised GANs
Connecting Generative Adversarial Networks and Actor Critic Methods, NIPS 2016 | David Pfau
Introduction to GANs, NIPS 2016 | Ian Goodfellow, OpenAI
Generating Faces with a Generative Adversarial Networks (GAN) in Keras/Tensorflow 2.0 (7.2)
Overcoming the Curse of Dimensionality and Mode Collapse - Ke Li