Workshop: Competition Track Friday
Hugo Jair Escalante, Katja Hofmann
Fri, Dec 11th @ 16:00 GMT – Sat, Dec 12th @ 01:45 GMT
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
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
16:00 – 16:15 GMT
Opening - Competition Track Session
Katja Hofmann, Hugo Jair Escalante
16:15 – 16:35 GMT
3D+texture garment reconstruction challenge design (data, metrics, tracks, etc)
Hugo Bertiche
16:35 – 17:00 GMT
3D+texture garment reconstruction challenge results
Meysam Madadi
17:00 – 17:03 GMT
Opening the L2RPN challenge @ NeurIPS2020
Antoine Marot
17:03 – 17:13 GMT
Winning the L2RPN challenge
Antoine Marot
17:13 – 17:23 GMT
A L2RPN Winning approach
Jixiang LU
17:23 – 17:33 GMT
The Best L2RPN wining approach
Bo Zhou
17:33 – 17:40 GMT
L2RPN Post Challenge open questions
Antoine Marot
17:40 – 17:45 GMT
Closing and ceremony award
Antoine Marot
18:00 – 18:03 GMT
Introducing the Hide-and-Seek privacy challenge
James Jordon
18:03 – 18:18 GMT
The importance of synthetic data
James Jordon
18:18 – 18:28 GMT
Synthetic data in the healthcare setting
James Jordon
18:28 – 18:38 GMT
What we learned from the Hide-and-Seek privacy challenge
James Jordon
18:38 – 18:43 GMT
Closing remarks
James Jordon
19:00 – 19:16 GMT
Background on black box optimization (BBO)
Ryan Turner
19:16 – 19:27 GMT
BBO challenge platform with Valohai
Juha Kiili
19:27 – 19:32 GMT
Spotlight for 1st place (BBO challenge)
Ryan Turner, Alexander Cowen-Rivers
19:32 – 19:37 GMT
Spotlight for 2nd place (BBO challenge)
Ryan Turner, Jiwei Liu
19:37 – 19:42 GMT
Spotlight for 3rd place (BBO challenge)
Ryan Turner, Mikita Sazanovich
22:00 – 22:07 GMT
Opening the SpaceNet 7 Challenge @ NeurIPS2020
Adam Van Etten
22:07 – 22:15 GMT
Introduction to SpaceNet
Jake Shermeyer
22:15 – 22:25 GMT
The SpaceNet 7 Dataset
Jesus Martinez-Manso
22:25 – 22:30 GMT
The SpaceNet 7 Metric
Adam Van Etten
22:30 – 22:40 GMT
The Winners of SpaceNet 7
Adam Van Etten
22:40 – 22:45 GMT
SpaceNet 7 Closing and Future Plans
Adam Van Etten
23:00 – 23:05 GMT
introduction to the 2020 NeurIPS education challenge
Angus Lamb
23:05 – 23:20 GMT
Competition overview: motivation, impact, dataset, tasks
Angus Lamb
23:20 – 23:30 GMT
Competition results and insights
Jack Wang
23:30 – 23:35 GMT
Beyond the competition: what's next?
Jack Wang
23:35 – 23:45 GMT
Q&A and discussion
Jack Wang, Angus Lamb
00:00 – 00:05 GMT
Traffic Map Movies - An Introduction to the Traffic4cast Challenge
Sepp Hochreiter
00:05 – 00:10 GMT
The Traffic4cast Competition Design and Data
Michael Kopp
00:10 – 00:12 GMT
The Best Traffic4Cast Submissions
David Kreil, D Kreil
00:12 – 00:17 GMT
1st prize: Utilizing UNet for the Future Traffic Map Prediction - Traffic4cast highlight talk
Sungbin Choi
00:17 – 00:22 GMT
2nd prize: TLab: Traffic Map Movie Forecasting Based on HR-NET - Traffic4cast highlight talk
Fanyou Wu
00:22 – 00:27 GMT
3rd prize: Towards Good Practices of U-Net for Traffic Forecasting - Traffic4cast highlight talk
Jingwei Xu
00:27 – 00:32 GMT
Graph Ensemble Net and the Importance of Feature & Loss Function Design for Traffic Prediction - Traffic4cast highlight talk
Qi Qi
00:32 – 00:37 GMT
Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction - Traffic4cast highlight talk
tijs Maas
00:37 – 00:45 GMT
Traffic4cast Award Ceremony, Outlook, and Follow Up Challenges
D Kreil
01:00 – 01:15 GMT
The Hateful Memes Challenge: Competition Overview
Douwe Kiela
01:15 – 01:45 GMT
The Hateful Memes Challenge: Live award ceremony and winner presentations
Douwe Kiela