Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detection

TL;DR

This paper introduces the Binarization-Aware Adjuster (BAA), a framework that aligns continuous model training with discrete decision-making, demonstrated through improved edge detection performance.

Contribution

The paper presents a theoretically grounded BAA framework that incorporates binarization characteristics into continuous optimization for discrete decision tasks.

Findings

BAA improves edge detection accuracy across models and datasets.

Incorporating BAA leads to consistent performance gains.

The framework effectively aligns training with decision behavior.

Abstract

Discrete decision tasks in machine learning exhibit a fundamental misalignment between training and inference: models are optimized with continuous-valued outputs but evaluated using discrete predictions. This misalignment arises from the discontinuity of discretization operations, which prevents decision behavior from being directly incorporated into gradient-based optimization. To address this issue, we propose a theoretically grounded framework termed the Binarization-Aware Adjuster (BAA), which embeds binarization characteristics into continuous optimization. The framework is built upon the Distance Weight Function (DWF), which modulates loss contributions according to prediction correctness and proximity to the decision threshold, thereby aligning optimization emphasis with decision-critical regions while remaining compatible with standard learning pipelines. We apply the proposed BAA framework to the edge detection (ED) task, a representative binary decision problem. Experimental results on representative models and datasets show that incorporating BAA into optimization leads to consistent performance improvements, supporting its effectiveness. Overall, this work establishes a principled approach for aligning continuous optimization with discrete decision behavior, with its effectiveness demonstrated in a concrete application setting.