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...
主要な著者: | Williams, DSW, Gadd, M, Newman, P, De Martini, D |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
IEEE
2024
|
類似資料
-
Mitigating distributional shift in semantic segmentation via uncertainty estimation from unlabeled data
著者:: Williams, DSW, 等
出版事項: (2024) -
Fool me once: robust selective segmentation via out-of-distribution detection with contrastive learning
著者:: Williams, DSW, 等
出版事項: (2021) -
Visual masking estimation based on structural uncertainty
著者:: Lin, Weisi, 等
出版事項: (2013) -
To exploit uncertainty masking for adaptive image rendering
著者:: Dong, Lu, 等
出版事項: (2013) -
Toward accurate hand mesh estimation via masked image modeling
著者:: Yanli Li, 等
出版事項: (2025-01-01)