DACL reports up to 2.77% Dice improvement and 14.69 mm HD95 reduction in fetal US segmentation under 5% labeled data via dual-agreement consistency between CNN and Transformer networks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation
DACL reports up to 2.77% Dice improvement and 14.69 mm HD95 reduction in fetal US segmentation under 5% labeled data via dual-agreement consistency between CNN and Transformer networks.