Tasks and submission:¶

1) Artefact detection: This task will be evaluated based on the results of the test dataset provided from a subset of the data collected for training

2) Semantic segmentation: This task will be evaluated based on the results of the test dataset provided from a subset of the data collected for training

3) Out-of-sample generalisation: This task will be evaluated based on the results of the test dataset provided exclusive from the training or other test datasets (data from the institution not taken in any other data)

Submission

Results should be submitted like the provided training ground truth annotations for each task category:

Category 1 (artefact detection): "csv file" of bounding box coordinates corresponding to each class (e.g. label, confidence, x1, y1, x2, y2).
Category 2 (semantic segmentation): image "label masks", integer valued for each image
Category 3 (out-of-sample generalisation): "csv file" of bounding box coordinates corresponding to each class (e.g. label, confidence, x1, y1, x2, y2).

Previous online submission strategy here: https://github.com/sharibox/EAD2019/blob/master/evaluation_ead2019/readme.md