📜 Rules

There several policies that participant are required to consider in order to be included in the competition:

• All final submissions should be in the form of docker containers and follow the provided template provided by the organizers to be tested successfully.
• Only fully automated methods are acceptable for participation in this challenge as the submission is in the form of docker containers. It is not possible to submit manual annotations or interactive methods.
• Submissions will be ranked solely based on their performance on the final test set and according to the criteria explained in the evaluation page.
• Using pre-trained models on general purpose datasets (like ImageNet) is allowed.
• Use of external data for model development is not permitted.
• Writing a technical paper for final submission is compulsory, otherwise the submission will not be considered.
• Users/teams can have multiple submissions on the preliminary test set to verify the quality of their methods. However, the number of submissions per day per user and for each task is limited to 2 in order to restrict test data hacking.
• For the final test set, only 2 submission is allowed for each user/team.
• Users can form a team and participate together. Teams can have different submissions as long as their submissions vary considerably based on the described methodology in their technical papers. Otherwise, organizers have the right to disqualify those submissions at their discretion.
• Members from the organizing team can participate in this challenge. If there is a method in the leaderboard submitted by the organizers, that method will not be taken into account for the final ranking

 Licence :

The data can only be used for the purpose and duration of the challenge. It cannot be distributed. As we did for previous challenges (https://ieee-dataport.org/open-access/cataracts), data will be released publicly after the challenge paper is accepted, under the terms of the “Creative Commons” Attribution
(CC-BY) license.