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

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...

תיאור מלא

מידע ביבליוגרפי
Main Authors: Williams, DSW, Gadd, M, Newman, P, De Martini, D
פורמט: Conference item
שפה:English
יצא לאור: IEEE 2024

פריטים דומים

פריטים דומים