Closed vict0rsch closed 3 years ago
Currently our ADVENT implementation uses target labels from deeplab v2 as GT to train the "segmentation" (ie masker for us). This is not how they do it in the paper so we should check w/ experiments what's best
It is not using target segmentation now (in the main_loss in the masker_loss).
Currently our ADVENT implementation uses target labels from deeplab v2 as GT to train the "segmentation" (ie masker for us). This is not how they do it in the paper so we should check w/ experiments what's best