The Edge-Boundary-Texture loss, a three-class weighted binary cross-entropy for edge detection, improves scores under a strict 1-pixel no-NMS protocol but not under standard NMS benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection
The Edge-Boundary-Texture loss, a three-class weighted binary cross-entropy for edge detection, improves scores under a strict 1-pixel no-NMS protocol but not under standard NMS benchmarks.