Official Website: http://www.ug2challenge.org/
We provide 6,000 real-world low light images captured during the nighttime, at teaching buildings, streets, bridges, overpasses, parks etc., all labeled with bounding boxes for of human face, as the main training and/or validation sets. There will be a hold-out testing set of 4,000 low-light images, with human face bounding boxes annotated.
There are 2 phases:
This competition only allows you to submit the prediction results (no code):
However, the winner and the two runner-ups are required to submit their model codes. Challenge organizers will test the reproducibility. Failure of reproducing the performance will lead to the result on the leaderboard marked as invalid.
The submissions are evaluated using the mAP_metric metric. The metric is re-scaled linearly between 0 and 1, 0 corresponding to a random guess and 1 to perfect predictions.
Registration must be made before the end of phase 1. You may submit 5 submissions every day and 100 in total.
Read carefully the following guidelines before submitting. Methods not complying with the guidelines will be disqualified.
Start: Feb. 1, 2021, midnight
Description: Dry-run phase: 100 dry-run data for debugging purpose only. This set is provided just to validate your prediction format (so you can work with our final testing in the end). mIoU on this set is not accurate due to small amount of data. Feedback are provided on this dry-run set only.
Start: April 30, 2021, midnight
Description: Final testing phase: The results on the testing set will be revealed when the organizers make them available.
May 1, 2021, 3 a.m.
You must be logged in to participate in competitions.
Sign In