A context-aware critical pixel mask loss improves topology preservation and gap closing for 2D and 3D segmentation.
Following other work on topology-preserving segmentation [3–8, 13], we use the two public 2D datasets, Massachusetts Roads (Roads) [19] and HRF-Retina [20]
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
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ContextLoss: Context Information for Topology-Preserving Segmentation
A context-aware critical pixel mask loss improves topology preservation and gap closing for 2D and 3D segmentation.