You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The paper said, "we do not have ground truth segmentation label.". I can understand there is no segmentation mask for detection, but why is there no segmentation mask for instance segmentation task?
The text was updated successfully, but these errors were encountered:
Hi @waxnkw, thanks for your interest in our work. Here we want to say we don't have ground truth segmentation labels like semantic segmentation. For COCO, we cannot assign labels to the background regions if we only use the instance segmentation labels.
We generate the segmentation mask using the bounding boxes or instance mask labels. We assign the corresponding labels for the foreground objects and set the rest regions as the background.
The paper said, "we do not have ground truth segmentation label.". I can understand there is no segmentation mask for detection, but why is there no segmentation mask for instance segmentation task?
The text was updated successfully, but these errors were encountered: