Michal Šustr presents LOGAN: latent optimisation for generative adversarial networks
On 2020-01-09 11:00
at G205, Karlovo náměstí 13, Praha 2
Reading group on the work "LOGAN: latent optimisation for generative
adversarial networks" by Yan Wu, Jeff Donahue, David Balduzzi, Karen Simonyan,
Timothy Lillicrap.
Paper abstract: Training generative adversarial networks requires balancing of
delicate adversarial dynamics. Even with careful tuning, training may diverge
or end up in a bad equilibrium with dropped modes. In this work, we introduce a
new form of latent optimisation inspired by the CS-GAN and show that it
improves adversarial dynamics by enhancing interactions between the
discriminator and the generator. We develop supporting theoretical analysis
from the perspectives of differentiable games and stochastic approximation. Our
experiments demonstrate that latent optimisation can significantly improve GAN
training, obtaining state-of-the-art performance for the ImageNet (128 x 128)
dataset. Our model achieves an Inception Score (IS) of 148 and an Frechet
Inception Distance (FID) of 3.4, an improvement of 17% and 32% in IS and FID
respectively, compared with the baseline BigGAN-deep model with the same
architecture and number of parameters.
The reading group will include material from relevant prior work, in particular
the SGA approach [Letcher et al.,Differentiable Game Mechanics
]
Paper URL: https://arxiv.org/pdf/1912.00953.pdf
Instructions for participants: The reading group studies the literature in the
field of pattern recognition and computer vision. At each meeting one or more
papers are prepared for presentation by a single person, the presenter. The
meetings are open to anyone, disregarding their background. It is assumed that
everyone attending the reading group has, at least briefly, read the paper –
not necessarily understanding everything. Attendants should preferably send
questions about the unclear parts to the speaker at least one day in advance.
During the presentation we aim to have a fruitful discussion, a critical
analysis of the paper, as well as brainstorming for creative extensions.
See the page of reading groups
http://cmp.felk.cvut.cz/~toliageo/rg/index.html
adversarial networks" by Yan Wu, Jeff Donahue, David Balduzzi, Karen Simonyan,
Timothy Lillicrap.
Paper abstract: Training generative adversarial networks requires balancing of
delicate adversarial dynamics. Even with careful tuning, training may diverge
or end up in a bad equilibrium with dropped modes. In this work, we introduce a
new form of latent optimisation inspired by the CS-GAN and show that it
improves adversarial dynamics by enhancing interactions between the
discriminator and the generator. We develop supporting theoretical analysis
from the perspectives of differentiable games and stochastic approximation. Our
experiments demonstrate that latent optimisation can significantly improve GAN
training, obtaining state-of-the-art performance for the ImageNet (128 x 128)
dataset. Our model achieves an Inception Score (IS) of 148 and an Frechet
Inception Distance (FID) of 3.4, an improvement of 17% and 32% in IS and FID
respectively, compared with the baseline BigGAN-deep model with the same
architecture and number of parameters.
The reading group will include material from relevant prior work, in particular
the SGA approach [Letcher et al.,Differentiable Game Mechanics
]
Paper URL: https://arxiv.org/pdf/1912.00953.pdf
Instructions for participants: The reading group studies the literature in the
field of pattern recognition and computer vision. At each meeting one or more
papers are prepared for presentation by a single person, the presenter. The
meetings are open to anyone, disregarding their background. It is assumed that
everyone attending the reading group has, at least briefly, read the paper –
not necessarily understanding everything. Attendants should preferably send
questions about the unclear parts to the speaker at least one day in advance.
During the presentation we aim to have a fruitful discussion, a critical
analysis of the paper, as well as brainstorming for creative extensions.
See the page of reading groups
http://cmp.felk.cvut.cz/~toliageo/rg/index.html