Machine Learning Coffee seminar: "Progressive Growing of GANs for Improved Quality, Stability, and Variation" Tero Karras

2018-09-17 09:00:00 2018-09-17 10:00:00 Europe/Helsinki Machine Learning Coffee seminar: "Progressive Growing of GANs for Improved Quality, Stability, and Variation" Tero Karras Weekly seminars held jointly by Aalto University and the University of Helsinki. http://cs.aalto.fi/en/midcom-permalink-1e8ad09e3f81b3aad0911e8bf7f7b8d680732c132c1 Otakaari 2, 02150, Espoo

Weekly seminars held jointly by Aalto University and the University of Helsinki.

17.09.2018 / 09:00 - 10:00

Helsinki region machine learning researchers will start our week by an exciting machine learning talk. The aim is to gather people from different fields of science with interest in machine learning. Porridge and coffee is served at 9:00 and the talk will begin at 9:15.

Subscribe to the mailing list where seminar topics are announced beforehand.

Venue: Seminar room T6, CS building, Konemiehentie 2
Date: Monday 17.9.2018

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Tero Karras
Research Scientist, NVIDIA

Abstract: We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen, ICLR 2018

**

See the next talks at the seminar webpage.

Please spread the news and join us for our weekly habit of beginning the week by an interesting machine learning talk!

Welcome!