Fermi Denoising

Organized by mariia - Current server time: July 9, 2020, 1:47 p.m. UTC

Previous

TBN
Aug. 29, 2019, midnight UTC

Current

Training2
April 21, 2019, 10:13 a.m. UTC

End

Competition Ends
Jan. 1, 2020, midnight UTC

Fermi denoising

 

Fermi Denoising: Evaluation

The problem is an object detection problem. Each sample (an observation) is np.array of 200x200, presenting number of photons per pixel. You must predict the positions of point sources (we are not interested in the brigthness for the moment).  
You are given for training X_train images and y_train array of corresponding source coordinates. You must train a model which predicts an array of point sources coordinates for a given image.  

There are 2 phases:

  • Phase 1: development phase. We provide you with training data and its corresponding list of point source coordinates and validation and test data without list of corrdinates. Make predictions for both datasets. However, you will receive feed-back on your performance on the validation set only. The performance of your LAST submission will be displayed on the leaderboard.
  • Phase 2: final phase. You do not need to do anything. Your last submission of phase 1 will be automatically forwarded. Your performance on the test set will appear on the leaderboard when the organizers finish checking the submissions.

This competition allows you to submit either:

  • A pre-trained prediction model.
  • A prediction model that must be trained and tested.

The submissions are evaluated using the chosen metric. This metric computes the sum of the distances from each real source to the closest source from the predicted list of sources and the distances from each predicted sources to the closest source from the list of real sources. The perfect prediction returns 0.

Fermi: Rules

Submissions must be made before the end of phase 1. 

 

Training

Start: Feb. 10, 2019, midnight

Training2

Start: April 21, 2019, 10:13 a.m.

Testing

Start: May 16, 2019, midnight

Training

Start: Aug. 29, 2019, midnight

TBN

Start: Aug. 20, 2019, midnight

TBN

Start: Aug. 29, 2019, midnight

TBN

Start: Aug. 21, 2019, 7 p.m.

Training

Start: Aug. 21, 2019, midnight

Training

Start: Aug. 21, 2019, midnight

Training

Start: Aug. 21, 2019, midnight

Training

Start: Aug. 21, 2019, midnight

Training

Start: Aug. 21, 2019, midnight

Training

Start: Aug. 21, 2019, midnight

Competition Ends

Jan. 1, 2020, midnight

You must be logged in to participate in competitions.

Sign In