Target-informed self-supervised pretraining via masked image modeling and contrastive learning, plus a confidence-aware infusion head, yields over 6% Dice improvement on unlabeled target-domain POCUS images for pediatric fracture assessment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision
Target-informed self-supervised pretraining via masked image modeling and contrastive learning, plus a confidence-aware infusion head, yields over 6% Dice improvement on unlabeled target-domain POCUS images for pediatric fracture assessment.