We are happy to announce that the test data for the ImageCLEFcoral task at CLEF 2020 has been released. The test data contains images from four different locations:
- same location as training set
- similar location to training set
- geographically similar to training set
- geographically distinct from training set
Participants will be required to annotate and localise coral reef images by labelling the images with types of benthic substrate together. Each image is provided with possible class types.
The data is accessible through the crowdAI platform: https://www.aicrowd.com/challenges/imageclef-2020-coral-annotation-and-localisation/clef_task
Remember that only participants with signed End User Agreement (EUA) will have access to the data.
For more details and updates, please visit the task website at: https://www.imageclef.org/2020/coral
And join our mailing list: https://groups.google.com/forum/#!forum/imageclefcoral
If you participate in this task, you may want also to check the DrawnUI Task which addresses a similar classification problem, but in a different use case scenario. For more information see: https://www.imageclef.org/2020/drawnui
Dr Alba García Seco de Herrera PhD
Lecturer
Department of Computer Science and Electronic Engineering (CSEE)
University of Essex
T +44 (0) 1206 872907