Alexei Efros: Self-supervision, Meta-supervision, Curiosity: Making Computers Study Harder
Prof. Alexei Efros gave lecture at CIIRC (www.ciirc.cvut.cz) on 25.5.2018.
The lecture was organized by the IMPACT Project (http://impact.ciirc.cvut.cz).
Abstract:
Computer vision has made impressive gains through the use of deep learning models, trained with large-scale labeled data. However, labels require expertise and curation and are expensive to collect. Even worse, direct semantic supervision often leads the learning algorithms “cheating” and taking shortcuts, instead of actually doing the work. In this talk, I will briefly summarize several of my group’s efforts to combat this using self-supervision, meta-supervision, and curiosity — all ways of using the data as its own supervision. These lead to practical applications in image synthesis (such as pix2pix and cycleGAN), image forensics, audio-visual source separation, etc.
Bio:
Alexei Efros is a professor of Electrical Engineering and Computer Sciences at UC Berkeley. Before 2013, he was nine years on the faculty of Carnegie Mellon University, and has also been affiliated with École Normale Supérieure/INRIA and University of Oxford. His research is in the area of computer vision and computer graphics, especially at the intersection of the two. He is particularly interested in using data-driven techniques to tackle problems where large quantities of unlabeled visual data are readily available. Efros received his PhD in 2003 from UC Berkeley. He is a recipient of the Sloan Fellowship (2008), Guggenheim Fellowship (2008), SIGGRAPH Significant New Researcher Award (2010), 3 Helmholtz Test-of-Time Prizes (1999, 2003, 2005), and the ACM Prize in Computing (2016).
Видео Alexei Efros: Self-supervision, Meta-supervision, Curiosity: Making Computers Study Harder канала CIIRC ČVUT
The lecture was organized by the IMPACT Project (http://impact.ciirc.cvut.cz).
Abstract:
Computer vision has made impressive gains through the use of deep learning models, trained with large-scale labeled data. However, labels require expertise and curation and are expensive to collect. Even worse, direct semantic supervision often leads the learning algorithms “cheating” and taking shortcuts, instead of actually doing the work. In this talk, I will briefly summarize several of my group’s efforts to combat this using self-supervision, meta-supervision, and curiosity — all ways of using the data as its own supervision. These lead to practical applications in image synthesis (such as pix2pix and cycleGAN), image forensics, audio-visual source separation, etc.
Bio:
Alexei Efros is a professor of Electrical Engineering and Computer Sciences at UC Berkeley. Before 2013, he was nine years on the faculty of Carnegie Mellon University, and has also been affiliated with École Normale Supérieure/INRIA and University of Oxford. His research is in the area of computer vision and computer graphics, especially at the intersection of the two. He is particularly interested in using data-driven techniques to tackle problems where large quantities of unlabeled visual data are readily available. Efros received his PhD in 2003 from UC Berkeley. He is a recipient of the Sloan Fellowship (2008), Guggenheim Fellowship (2008), SIGGRAPH Significant New Researcher Award (2010), 3 Helmholtz Test-of-Time Prizes (1999, 2003, 2005), and the ACM Prize in Computing (2016).
Видео Alexei Efros: Self-supervision, Meta-supervision, Curiosity: Making Computers Study Harder канала CIIRC ČVUT
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Lecture 7 Self-Supervised Learning -- UC Berkeley Spring 2020 - CS294-158 Deep Unsupervised LearningBen Goertzel:From Here to Human-Level AGI in 4 Simple StepsJohn Hennessy and David Patterson 2017 ACM A.M. Turing Award LectureWhy is life the way it is? Michael Faraday Prize Lecture - Dr Nick LaneDeep Learning: A Crash CourseEverything wrong with statistics (and how to fix it)Self-Supervision as a Path to a Post-Dataset Era - Alexei Alyosha EfrosSacha Arnoud, Director of Engineering, Waymo - MIT Self-Driving Cars30.5.2018: Peter Staněk - Architektúra ľudského mozgu a umelá inteligenciaThe Einstein Lecture: The Quantum Computing RevolutionYann LeCun: "Energy-Based Self-Supervised Learning"Ben Goertzel: Questions after the talk From Here to Human-Level AGI in 4 Simple StepsThe Edge of Exponential Technologies - Ramez NaamBig Self-Supervised Models are Strong Semi-Supervised Learners (Paper Explained)Imagining a Post-Dataset Era (Alexei Efros, UC Berkeley)Yann LeCun: “AI Breakthroughs & Obstacles to Progress, Mathematical and Otherwise”You and AI – the history, capabilities and frontiers of AI[Dissertation Talk] Image Synthesis for Self-Supervised Representation Learning (4/18)Bmva Symposium Video Understanding Andrew ZissermanDavid Fouhey - "Understanding how to get to places and do things" 25 Oct 2018