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...
Main Authors: | Williams, DSW, Gadd, M, Newman, P, De Martini, D |
---|---|
Format: | Conference item |
Language: | English |
Published: |
2024
|
Similar Items
-
Mitigating distributional shift in semantic segmentation via uncertainty estimation from unlabelled data
by: Williams, DSW, et al.
Published: (2024) -
Fool me once: robust selective segmentation via out-of-distribution detection with contrastive learning
by: Williams, DSW, et al.
Published: (2021) -
Antibiotics for asthma attacks: masking uncertainty
by: Ramakrishnan, S, et al.
Published: (2021) -
Generalizable stereo depth estimation with masked image modelling
by: Samyakh Tukra, et al.
Published: (2024-04-01) -
Masked Modeling-Based Ultrasound Image Classification via Self-Supervised Learning
by: Kele Xu, et al.
Published: (2024-01-01)