2 papers
cs.CV2025
Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection
Hao Shu
Edge detection (ED) remains a fundamental task in computer vision, yet its performance is often hindered by the ambiguous nature of non-edge pixels near object boundaries. The wide…
cs.CV2025
Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detection
Hao Shu
Discrete decision tasks in machine learning exhibit a fundamental misalignment between training and inference: models are optimized with continuous-valued outputs but evaluated usi…