Learning2AdaptForStereo
Learning2AdaptForStereo copied to clipboard
Question about adaptation?
Thanks for the great work! I want to know if the weighted mask will be updated in online adaptation phase using a small amount of gt labels?
If weighted mask is not updated in online adaptation,maybe better unspervised loss can bring better performence?
No gt labels are used online. The weighted mask is predicted from RGB data and the small network predicting it is not updated.
Better unsupervised losses can definitely improve performances.