Masked γ-SSL: learning uncertainty estimation via masked image modeling

This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling (MIM) approach, which is robust to augmentation hyper-parame...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí: Williams, DSW, Gadd, M, Newman, P, De Martini, D
Formáid: Conference item
Teanga:English
Foilsithe / Cruthaithe: IEEE 2024

Míreanna comhchosúla