( events)   Timezone: »  
Fri Dec 11 08:00 AM -- 05:45 PM (PST)
Competition Track Friday
Hugo Jair Escalante · Katja Hofmann

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:


Opening - Competition Track Session (Intro)
3D+texture garment reconstruction challenge design (data, metrics, tracks, etc) (Live oral presentation)
3D+texture garment reconstruction challenge results (Live oral presentation)
Opening the L2RPN challenge @ NeurIPS2020 (Intro)
Winning the L2RPN challenge (Oral presentation)
A L2RPN Winning approach (Oral presentation)
The Best L2RPN wining approach (Oral presentation)
L2RPN Post Challenge open questions (Oral presentation)
Closing and ceremony award (Outro)
Introducing the Hide-and-Seek privacy challenge (Intro)
The importance of synthetic data (Oral presentation)
Synthetic data in the healthcare setting (Oral presentation)
What we learned from the Hide-and-Seek privacy challenge (Oral presentation)
Closing remarks (Outro)
Background on black box optimization (BBO) (Oral presentation)
BBO challenge platform with Valohai (Oral presentation)
Spotlight for 1st place (BBO challenge) (Oral presentation)
Spotlight for 2nd place (BBO challenge) (Oral presentation)
Spotlight for 3rd place (BBO challenge) (Oral presentation)
Opening the SpaceNet 7 Challenge @ NeurIPS2020 (Oral presentation)
Introduction to SpaceNet (Oral presentation)
The SpaceNet 7 Dataset (Oral presentation)
The SpaceNet 7 Metric (Oral presentation)
The Winners of SpaceNet 7 (Oral presentation)
SpaceNet 7 Closing and Future Plans (Oral presentation)
introduction to the 2020 NeurIPS education challenge (Oral presentation)
Competition overview: motivation, impact, dataset, tasks (Oral presentation)
Competition results and insights (Oral presentation)
Beyond the competition: what's next? (Oral presentation)
Q&A and discussion (Outro)
Traffic Map Movies - An Introduction to the Traffic4cast Challenge (Oral presentation)
The Traffic4cast Competition Design and Data (Oral presentation)
The Best Traffic4Cast Submissions (Intro)
1st prize: Utilizing UNet for the Future Traffic Map Prediction - Traffic4cast highlight talk (Oral presentation)
2nd prize: TLab: Traffic Map Movie Forecasting Based on HR-NET - Traffic4cast highlight talk (Oral presentation)
3rd prize: Towards Good Practices of U-Net for Traffic Forecasting - Traffic4cast highlight talk (Oral presentation)
Graph Ensemble Net and the Importance of Feature & Loss Function Design for Traffic Prediction - Traffic4cast highlight talk (Oral presentation)
Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction - Traffic4cast highlight talk (Oral presentation)
Traffic4cast Award Ceremony, Outlook, and Follow Up Challenges (Discussion panel)
The Hateful Memes Challenge: Competition Overview (Oral presentation)
The Hateful Memes Challenge: Live award ceremony and winner presentations (Discussion panel)