Bounding boxes requirement during training?
zshn25 opened this issue · comments
Great work guys, I was wondering if you require bounding box labels during training? There’s a brief mention of this in the video and also in the paper. Just wanted to make sure.
Yes, it requires bounding boxes. "In this work, we aim to remove the mask-annotation requirement. We propose MaskFreeVIS, achieving highly competitive VIS performance, while only using cheap bounding box annotations for the object state."