Dear organizers,
When selecting the best model based during validation, are we restricted to only using data from the training sets authorized for the specific task/subtask the model is targeting, or are we allowed to make use of additional validation sets, e.g. LFW?
Thank you.
Posted by: IRI @ Oct. 24, 2023, 8:40 a.m.Dear IRI,
Alternative datasets (e.g. LFW) are not considered for validation.
Participants are required to use data from the allowed training sets.
Posted by: FRCSyn @ Oct. 25, 2023, 8:18 a.m.