Image edge detection (ED) faces a fundamental mismatch between training and inference: models are trained using continuous-valued outputs but evaluated using binary predictions. This misalignment, caused by the non-differentiability of binarization, weakens the link between learning objectives and actual task performance. In this paper, we propose a theoretical method to design a Binarization-Aware Adjuster (BAA), which explicitly incorporates binarization behavior into gradient-based optimization. At the core of BAA is a novel loss adjustment mechanism based on a Distance Weight Function (DWF), which reweights pixel-wise contributions according to their correctness and proximity to the decision boundary. This emphasizes decision-critical regions while down-weighting less influential ones. We also introduce a self-adaptive procedure to estimate the optimal binarization threshold for BAA, further aligning training dynamics with inference behavior. Extensive experiments across various architectures and datasets demonstrate the effectiveness of our approach. Beyond ED, BAA offers a generalizable strategy for bridging the gap between continuous optimization and discrete evaluation in structured prediction tasks.
View on arXiv