- June 9, 2015: All slides are now online
- June 7, 2015: Tutorial takes place
- May 5, 2015: Schedule posted
- January 8, 2015: Organization of the ImageNet Large Scale Visual Recognition Challenge Tutorial is underway
IntroductionThe ImageNet Large Scale Visual Recognition Challenge (ILSVRC) is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions.
This half-day tutorial will focus on providing a high-level overview of the challenge, with the goal of sharing some of the lessons learned by the organizers and participants in the past five years. Concretely, we aim to:
- Present the attendees with a historical background of the challenge, which would help them to place the latest research innovations in perspective.
- Familiarize the attendees with the process of large-scale crowdsourced data collection, enabling them to better understand the ImageNet dataset as well as collect their own large-scale datasets.
- Provide the attendees with tools and techniques, which would allow them to enter the next ImageNet challenge.
The tutorial will be held the morning of June 7.
ILSVRC overview: past, present, and future
|9:15|| Jonathan Krause:
Lessons learned from large-scale crowdsourced data collection
|10:45|| Karen Simonyan:
ILSVRC essentials in light of recent developments
|11:30|| Yangqing Jia:
Getting started with your own ILSVRC submission
- Olga Russakovsky ( Stanford University )
- Jonathan Krause ( Stanford University )
- Karen Simonyan ( Google DeepMind )
- Yangqing Jia ( Google )