This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Workshop: Competition Track Friday

Hugo Jair Escalante, Katja Hofmann

2020-12-11T08:00:00-08:00 - 2020-12-11T17:45:00-08:00
Abstract: First session for the competition program at NeurIPS2020.

Machine learning competitions have grown in popularity and impact over the last decade, emerging as an effective means to advance the state of the art by posing well-structured, relevant, and challenging problems to the community at large. Motivated by a reward or merely the satisfaction of seeing their machine learning algorithm reach the top of a leaderboard, practitioners innovate, improve, and tune their approach before evaluating on a held-out dataset or environment. The competition track of NeurIPS has matured in 2020, its fourth year, with a considerable increase in both the number of challenges and the diversity of domains and topics. A total of 16 competitions are featured this year as part of the track, with 8 competitions associated to each of the two days. The list of competitions that ar part of the program are available here:

https://neurips.cc/Conferences/2020/CompetitionTrack

Chat

To ask questions please use rocketchat, available only upon registration and login.

Schedule

2020-12-11T08:00:00-08:00 - 2020-12-11T08:15:00-08:00
Opening - Competition Track Session
Katja Hofmann, Hugo Jair Escalante
2020-12-11T08:15:00-08:00 - 2020-12-11T08:35:00-08:00
3D+texture garment reconstruction challenge design (data, metrics, tracks, etc)
Hugo Bertiche
2020-12-11T08:35:00-08:00 - 2020-12-11T09:00:00-08:00
3D+texture garment reconstruction challenge results
Meysam Madadi
2020-12-11T09:00:00-08:00 - 2020-12-11T09:03:00-08:00
Opening the L2RPN challenge @ NeurIPS2020
Antoine Marot
2020-12-11T09:03:00-08:00 - 2020-12-11T09:13:00-08:00
Winning the L2RPN challenge
Antoine Marot
2020-12-11T09:13:00-08:00 - 2020-12-11T09:23:00-08:00
A L2RPN Winning approach
Jixiang LU
2020-12-11T09:23:00-08:00 - 2020-12-11T09:33:00-08:00
The Best L2RPN wining approach
Bo Zhou
2020-12-11T09:33:00-08:00 - 2020-12-11T09:40:00-08:00
L2RPN Post Challenge open questions
Antoine Marot
2020-12-11T09:40:00-08:00 - 2020-12-11T09:45:00-08:00
Closing and ceremony award
Antoine Marot
2020-12-11T10:00:00-08:00 - 2020-12-11T10:03:00-08:00
Introducing the Hide-and-Seek privacy challenge
James Jordon
2020-12-11T10:03:00-08:00 - 2020-12-11T10:18:00-08:00
The importance of synthetic data
James Jordon
2020-12-11T10:18:00-08:00 - 2020-12-11T10:28:00-08:00
Synthetic data in the healthcare setting
James Jordon
2020-12-11T10:28:00-08:00 - 2020-12-11T10:38:00-08:00
What we learned from the Hide-and-Seek privacy challenge
James Jordon
2020-12-11T10:38:00-08:00 - 2020-12-11T10:43:00-08:00
Closing remarks
James Jordon
2020-12-11T11:00:00-08:00 - 2020-12-11T11:16:00-08:00
Background on black box optimization (BBO)
Ryan Turner
2020-12-11T11:16:00-08:00 - 2020-12-11T11:27:00-08:00
BBO challenge platform with Valohai
Juha Kiili
2020-12-11T11:27:00-08:00 - 2020-12-11T11:32:00-08:00
Spotlight for 1st place (BBO challenge)
Ryan Turner, Alexander Cowen-Rivers
2020-12-11T11:32:00-08:00 - 2020-12-11T11:37:00-08:00
Spotlight for 2nd place (BBO challenge)
Ryan Turner, Jiwei Liu
2020-12-11T11:37:00-08:00 - 2020-12-11T11:42:00-08:00
Spotlight for 3rd place (BBO challenge)
Ryan Turner, Mikita Sazanovich
2020-12-11T14:00:00-08:00 - 2020-12-11T14:07:00-08:00
Opening the SpaceNet 7 Challenge @ NeurIPS2020
Adam Van Etten
2020-12-11T14:07:00-08:00 - 2020-12-11T14:15:00-08:00
Introduction to SpaceNet
Jake Shermeyer
2020-12-11T14:15:00-08:00 - 2020-12-11T14:25:00-08:00
The SpaceNet 7 Dataset
Jesus Martinez-Manso
2020-12-11T14:25:00-08:00 - 2020-12-11T14:30:00-08:00
The SpaceNet 7 Metric
Adam Van Etten
2020-12-11T14:30:00-08:00 - 2020-12-11T14:40:00-08:00
The Winners of SpaceNet 7
Adam Van Etten
2020-12-11T14:40:00-08:00 - 2020-12-11T14:45:00-08:00
SpaceNet 7 Closing and Future Plans
Adam Van Etten
2020-12-11T15:00:00-08:00 - 2020-12-11T15:05:00-08:00
introduction to the 2020 NeurIPS education challenge
Angus Lamb
2020-12-11T15:05:00-08:00 - 2020-12-11T15:20:00-08:00
Competition overview: motivation, impact, dataset, tasks
Angus Lamb
2020-12-11T15:20:00-08:00 - 2020-12-11T15:30:00-08:00
Competition results and insights
Jack Wang
2020-12-11T15:30:00-08:00 - 2020-12-11T15:35:00-08:00
Beyond the competition: what's next?
Jack Wang
2020-12-11T15:35:00-08:00 - 2020-12-11T15:45:00-08:00
Q&A and discussion
Jack Wang, Angus Lamb
2020-12-11T16:00:00-08:00 - 2020-12-11T16:05:00-08:00
Traffic Map Movies - An Introduction to the Traffic4cast Challenge
Sepp Hochreiter
2020-12-11T16:05:00-08:00 - 2020-12-11T16:10:00-08:00
The Traffic4cast Competition Design and Data
Michael Kopp
2020-12-11T16:10:00-08:00 - 2020-12-11T16:12:00-08:00
The Best Traffic4Cast Submissions
David Kreil, D Kreil
2020-12-11T16:12:00-08:00 - 2020-12-11T16:17:00-08:00
1st prize: Utilizing UNet for the Future Traffic Map Prediction - Traffic4cast highlight talk
Sungbin Choi
2020-12-11T16:17:00-08:00 - 2020-12-11T16:22:00-08:00
2nd prize: TLab: Traffic Map Movie Forecasting Based on HR-NET - Traffic4cast highlight talk
Fanyou Wu
2020-12-11T16:22:00-08:00 - 2020-12-11T16:27:00-08:00
3rd prize: Towards Good Practices of U-Net for Traffic Forecasting - Traffic4cast highlight talk
Jingwei Xu
2020-12-11T16:27:00-08:00 - 2020-12-11T16:32:00-08:00
Graph Ensemble Net and the Importance of Feature & Loss Function Design for Traffic Prediction - Traffic4cast highlight talk
Qi Qi
2020-12-11T16:32:00-08:00 - 2020-12-11T16:37:00-08:00
Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction - Traffic4cast highlight talk
tijs Maas
2020-12-11T16:37:00-08:00 - 2020-12-11T16:45:00-08:00
Traffic4cast Award Ceremony, Outlook, and Follow Up Challenges
D Kreil
2020-12-11T17:00:00-08:00 - 2020-12-11T17:15:00-08:00
The Hateful Memes Challenge: Competition Overview
Douwe Kiela
2020-12-11T17:15:00-08:00 - 2020-12-11T17:45:00-08:00
The Hateful Memes Challenge: Live award ceremony and winner presentations
Douwe Kiela