CVPR18: Tutorial: Part 1: Generative Adversarial Networks скачать в хорошем качестве

CVPR18: Tutorial: Part 1: Generative Adversarial Networks

Organizers: Jun-Yan Zhu Taesung Park Mihaela Rosca Phillip Isola Ian Goodfellow. Description: Generative adversarial networks (GANs) have been at the forefront of research on generative models in the last couple of years. GANs have been used for image genera-tion, image processing, image synthesis from captions, image editing, visual domain adaptation, data generation for visual recognition, and many other applications, often leading to state of the art results. This tutorial aims to provide a broad overview of generative adversarial networks, mainly including the following three parts: (1) theoretical foundations such as basic concepts, mechanisms, and theoretical considerations, (2) best practices of the current state-of-the-art GAN and conditional GAN models, including network architectures, objective functions, and other training tricks, and (3) computer vision applications including visual domain adaptation, image processing (e.g., restoration, inpainting, super-resolution), image synthesis and manipulation, video prediction and gener-ation, 3D modeling, synthetic data generation for visual recog-nition, robotic learning, and so on. Schedule: 0900 Introduction to Generative Adversarial Networks, Ian Goodfellow (Google Brain) 0930 Paired Image-to-Image Translation, Phillip Isola (MIT) 1000 Unpaired Image-to-Image Translation, Taesung Park (UC Berkeley and Jun-Yan Zhu, MIT) 1100 Can GANs Actually Learn the Distribution? Some Obstacles, Sanjeev Arora (Princeton) 1145 TBA, Emily Denton (NYU) 1330 Autoencoder, VAE, and GANs, Mihaela Rosca (Deepmind) 1400 TBA, Ming-Yu Liu (NVIDIA) 1430 Adversarial Domain Adaptation, Judy Hoffman (UC Berkeley) 1500 Afternoon Break & Live Demo 1530 TBA, Abhinav Gupta (CMU) 1600 Generative Adversarial Imitation Learning, Stefano Ermon (Stanford) 1630 Video Generation and Prediction, Carl Vondrick (Columbia Univ.) 1700 TBA, Alexei A. Efros (UC Berkeley)