Schedule and slides
22 October 2017
22 October 2017
Speakers
Speakers
9:45 Mihaela Rosca, DeepMind: Autoencoder GANs [slides (pdf)]
9:45 Mihaela Rosca, DeepMind: Autoencoder GANs [slides (pdf)]
10:15 Coffee break and live demo session: Jun-Yan Zhu and Taesung Park: iGAN / pix2pix / CycleGAN
10:15 Coffee break and live demo session: Jun-Yan Zhu and Taesung Park: iGAN / pix2pix / CycleGAN
11:00 Soumith Chintala, Facebook: GANs in the Wild [slides (pdf)]
11:00 Soumith Chintala, Facebook: GANs in the Wild [slides (pdf)]
11:30 Han Zhang, Rutgers University: Conditional GANs, StackGAN [slides (pdf)]
11:30 Han Zhang, Rutgers University: Conditional GANs, StackGAN [slides (pdf)]
12:00 Lucas Theis, Twitter: Evaluating Generative Models [slides (pdf)]
12:00 Lucas Theis, Twitter: Evaluating Generative Models [slides (pdf)]
12:30 Lunch
12:30 Lunch
14:00 Sanjeev Arora, Princeton University : Do GANs learn the distribution? [slides (pptx)]
14:00 Sanjeev Arora, Princeton University : Do GANs learn the distribution? [slides (pptx)]
14:45 Victor Lempitsky, Skoltech: Domain Adversarial Learning [slides (pdf)]
14:45 Victor Lempitsky, Skoltech: Domain Adversarial Learning [slides (pdf)]
15:15 Jun-Yan Zhu, UC Berkeley: Visual Synthesis and Manipulation with GANs [slides(pdf)] [slides(pptx)]
15:15 Jun-Yan Zhu, UC Berkeley: Visual Synthesis and Manipulation with GANs [slides(pdf)] [slides(pptx)]
15:45 Coffee break and live demo session: Jun-Yan Zhu and Taesung Park: iGAN / pix2pix / CycleGAN
15:45 Coffee break and live demo session: Jun-Yan Zhu and Taesung Park: iGAN / pix2pix / CycleGAN
16:30 David Pfau, DeepMind: Connections between adversarial training and RL
16:30 David Pfau, DeepMind: Connections between adversarial training and RL
17:00 Alexei Efros, UC Berkeley: GANs as Learned Loss Functions
17:00 Alexei Efros, UC Berkeley: GANs as Learned Loss Functions