May 27th, 2019
National Olympics Memorial Youth Center, Tokyo, Japan
Scaling-up Deep Learning for Autonomous Driving
Jose M. Alvarez
Senior Research Scientist, NVIDIA, Australian National Univerisity
Jose M. Alvarez is a Senior Deep Learning Engineer at NVIDIA working on scaling-up deep learning for autonomous driving. Previously, he was a senior researcher at Toyota Research Institute and at Data61/CSIRO (formerly NICTA) working on deep learning for large scale dynamic scene understanding. Prior to that, he worked as a postdoctoral researcher at New York University under the supervision of Prof. Yann LeCun. He graduated with his Ph.D. from Autonomous University of Barcelona (UAB) in October 2010, with focus on robust road detection under real-world driving conditions. Dr. Alvarez did research stays at the University of Amsterdam (in 2008 and 2009) and the Electronics Research Group at Volkswagen (in 2010) and Boston College. Since 2014, he has served as an associate editor for IEEE Transactions on Intelligent Transportation Systems.
Abstract: Deep learning has rapidly moved from research to be a key component in providing industrial impact in areas such as autonomous driving. From initial semantic segmentation to more recent advanced systems, these algorithms continuously increase the consumption of data and computational resources. The amount of data being acquired, and the need of annotations keep growing exponentially and open new challenges to improve accuracy and to achieve the desired safety level. In this talk, I will explore some of these challenges along with our proposed solutions in terms of active learning, computational efficiency and the efficient use of synthetic data for training deep networks.
3D Computer Vision and Open3D
Research Scientist, Intel Corporation
Jaesik Park is a Research Scientist at Intel. He received his Bachelor degree from Hanyang University in 2009. He received his Master degree and PhD degree from KAIST in 2011 and 2015, respectively. He is a recipient of Microsoft Research Asia Fellowship in 2011. After he joined Intelligent Systems Lab at Intel in 2015, he authored/co-authored academic papers about Open3D library, depth camera based geometry recovery, an automatic photogrammetry evaluation system, 3D semantic segmentation, and surface registration algorithms.
Abstract: The world is 3D — recovering and understanding a 3D scene is a fundamental task for intelligent systems. This talk will be devoted to how to capture 3D data and how to apply 3D data to machinery. The tutorial overviews several high quality 3D reconstruction techniques, and introduces a new convolution kernel designed for scene understanding and point-wise prediction. The next topic is Open3D — a new open source library that provides basic and advanced 3D processing algorithms with easy user interface. This tutorial will introduce basic usage of Open3D, and how to utilize it for custom 3D computer vision projects.