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.
Boosting edge detection with pixel-wise feature selection: The extractor-selector paradigm, 2025
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
REJECT 1roles
background 1polarities
background 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.