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 |
---|---|
格式: | Conference item |
語言: | English |
出版: |
IEEE
2024
|
相似書籍
-
Mitigating distributional shift in semantic segmentation via uncertainty estimation from unlabeled data
由: Williams, DSW, et al.
出版: (2024) -
Fool me once: robust selective segmentation via out-of-distribution detection with contrastive learning
由: Williams, DSW, et al.
出版: (2021) -
Visual masking estimation based on structural uncertainty
由: Lin, Weisi, et al.
出版: (2013) -
To exploit uncertainty masking for adaptive image rendering
由: Dong, Lu, et al.
出版: (2013) -
Toward accurate hand mesh estimation via masked image modeling
由: Yanli Li, et al.
出版: (2025-01-01)