Pixel SkelNetOn - CVPR 2019

Organized by ilkedemir - Current server time: May 20, 2019, 10:47 p.m. UTC


March 29, 2019, 6 p.m. UTC


Feb. 19, 2019, 6 p.m. UTC


Competition Ends
April 3, 2019, 11:59 p.m. UTC

Pixel SkelNetOn

As the most common data format for segmentation or pixel-wise classification neural network models, our first domain poses the challenge of extracting the skeleton pixels from a given shape in an image. The participants need to overcome fundamental problems like class imbalance, global structure search, and robustness constraints while reducing the given shapes to clean skeleton pixels. Although the output will not be a true geometric representation, it is easier to convert the skeleton pixels to a vector format. This is a binary classification problem to detect the skeleton pixels for a given shape image.

This competition is a part of Deep Learning for Geometric Shape Understanding Workshop, in association with CVPR 2019.
For details about other SkelNetOns and the workshop: http://ubee.enseeiht.fr/skelneton/
For details about the dataset and example baselines: https://arxiv.org/abs/1903.09233

Please refer to the following paper if you participate in this challenge or use the dataset for your approach: 

author = {{Demir}, Ilke and {Hahn}, Camilla and {Leonard}, Kathryn and {Morin},
Geraldine and {Rahbani}, Dana and {Panotopoulou}, Athina and {Fondevilla},
Amelie and {Balashova}, Elena and {Durix}, Bastien and {Kortylewski}, Adam},
title = "{SkelNetOn 2019 Dataset and Challenge on Deep Learning for Geometric Shape Understanding}",
journal = {arXiv e-prints},
keywords = {Computer Science - Computer Vision and Pattern Recognition},
year = "2019",
eprint = {1903.09233},
primaryClass = {cs.CV}


The problem is a binary classification problem. Each input is a shape image. You must predict a skeleton image for the input, i.e., a binary image of the same height and width as the input image.

There are 2 phases:

  • Phase 1: Development phase. We provide you with labeled training data and unlabeled validation and test data. 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. The unlabeled testing dataset will be released. You can submit your predictions on the test dataset to CodaLab. Your performance on the test set will appear on the leaderboard when the organizers finish verifying the submissions.

You only need to submit the prediction results (no code). However you need to submit a short paper of 3 pages (+1 page for references) before March 25 April 3 to be eligible for the prizes. We will evaluate your methodology and your results in parallel. Paper submission will be open in the workshop CMT site, and please use the CVPR paper template.

The submissions are evaluated using the F1 metric.


This challenge is governed by SkelNetOn Rules. For academic use of the datasets within and outside this competition, please cite the following papers.
[1] SkelNetOn dataset paper (coming soon!)
[2] A. M. Bronstein, M. M. Bronstein, A. M. Bruckstein, R. Kimmel, Analysis of two- dimensional non-rigid shapes, Intl. J. Computer Vision (IJCV), Vol. 78/1, pp. 67-88, June 2008.
[3] Sebastian TB, Klein PN, Kimia BB (2004) Recognition of shapes by editing their shock graphs. IEEE Trans Pattern Anal Mach Intell 26(5):550–571
[4] Leonard, K., Morin, G., Hahmann, S., & Carlier, A. (2016). A 2D shape structure for decomposition and part similarity. 2016 23rd International Conference on Pattern Recognition (ICPR), 3216-3221.



Start: Feb. 19, 2019, 6 p.m.

Description: Development phase: Directly submit your results on validation data; feedback is provided on the validation set only.


Start: March 29, 2019, 6 p.m.

Description: Final phase: Please complete this phase using the test dataset. The results on the test set will be revealed when the organizers make them available.

Competition Ends

April 3, 2019, 11:59 p.m.

You must be logged in to participate in competitions.

Sign In
# Username Score
1 digitalspecialists 0.7710
2 opanichev 0.7582
3 sabarinathan 0.7480