VisDA 2020: Domain Adaptive Pedestrian Re-identification

Organized by weijian - Current server time: July 6, 2020, 10:04 a.m. UTC

Previous

Training and Validation Data Released
May 1, 2020, midnight UTC

Current

Testing Data Released
June 26, 2020, midnight UTC

End

Competition Ends
July 25, 2020, midnight UTC

Welcome!

It is well known that the success of machine learning methods on visual recognition tasks is highly dependent on access to large labeled datasets. Unfortunately, performance often drops significantly when the model is presented with data from a new deployment domain which it did not see in training, a problem known as dataset shift. The VisDA challenge aims to test domain adaptation methods’ ability to transfer source knowledge and adapt it to novel target domains.
This year’s challenge focuses on Domain Adaptive Pedestrian Re-identification, where the source and target domains have completely different classes (pedestrian IDs). The particular task is to retrieve the pedestrian instances of the same ID as the query image. This problem is significantly different from previous VisDA challenges, where the source and target domains share some overlapping classes. Moreover, ID matching depends on fine-grained details, making the problem harder than before.

  • Domain Adaptive Pedestrian Re-identification

For details and instructions on how to participate, please visit the VisDA challenge website, where you can download the datasets and development kits.

 

Evaluation Criteria

  • The final rank will be determined by the overall accuracy on the target test set. The evaluation metrics used to rank the performance of each team will be mean Average Precision (mAP) and Cumulated Matching Characteristics (CMC) curve. For more details, please see VisDA 2020 challenge.
  • The leaderboard will show your CodaLab username, not your team name. Do not use multiple accounts to submit for one team, and limit the number of submissions to the quota specified in the "Participate" section.
  • The main leaderboard shows the results of adapted models and will be used to determine the final team ranks.

 

Terms and Conditions

For terms and conditions, please see the challenge website.

Please follow the rules.

Training and Validation Data Released

Start: May 1, 2020, midnight

Description: Development phase: create models and submit them or directly submit results on validation data; feed-back are provided on the validation set.

Testing Data Released

Start: June 26, 2020, midnight

Description: The results on the test set will be revealed when the organizers make them available.

Competition Ends

July 25, 2020, midnight

You must be logged in to participate in competitions.

Sign In