HELPNet uses hierarchical jigsaw consistency, entropy-weighted pseudo-labels, and structural priors to bring scribble-supervised medical segmentation close to fully supervised performance.
, author Wang, X
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation
HELPNet uses hierarchical jigsaw consistency, entropy-weighted pseudo-labels, and structural priors to bring scribble-supervised medical segmentation close to fully supervised performance.