A quasi-concavity formulation turns global convexity into local differentiable inequalities on a segmentation mask and its derivatives, yielding a convolutional loss that unifies prior convex shape models.
Convexity shape prior for binary segmenta- tion.IEEE Transactions on Pattern Analysis & Machine In- telligence, 39(02):258–271, 2017
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
-
D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation
A quasi-concavity formulation turns global convexity into local differentiable inequalities on a segmentation mask and its derivatives, yielding a convolutional loss that unifies prior convex shape models.