Med-OoD adds background-only 'OOD' patches from the ID dataset as negative samples with zero-mask Dice loss, claiming modest gains on Lizard but an internally inconsistent 76.1% mIoU for the OOD-only case.
Revisiting neural scaling laws in language and vision,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Out-of-distribution data supervision towards biomedical semantic segmentation
Med-OoD adds background-only 'OOD' patches from the ID dataset as negative samples with zero-mask Dice loss, claiming modest gains on Lizard but an internally inconsistent 76.1% mIoU for the OOD-only case.