Abstract
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 widely adopted Weighted Binary Cross-Entropy (WBCE) loss treats all non-edge pixels uniformly, overlooking the structural nuances around edges and often resulting in blurred predictions. In this paper, we propose the Edge-Boundary-Texture (EBT) loss, a novel objective that explicitly divides pixels into three categories, edge, boundary, and texture, and assigns each a distinct supervisory weight. This tri-class formulation enables more structured learning by guiding the model to focus on both edge precision and contextual boundary localization. We theoretically show that the EBT loss generalizes the WBCE loss, with the latter becoming a limit case. Extensive experiments across multiple benchmarks demonstrate the superiority of the EBT loss both quantitatively and perceptually. Furthermore, the consistent use of unified hyperparameters across all models and datasets, along with robustness to their moderate variations, indicates that the EBT loss requires minimal fine-tuning and is easily deployable in practice.
Abstract (translated)
边缘检测（ED）仍然是计算机视觉中的基本任务，但其性能常常受到对象边界附近非边缘像素模糊性质的限制。广泛采用的加权二元交叉熵（WBCE）损失函数对所有非边缘像素一视同仁，忽略了边缘周围的结构细节，通常导致预测结果模糊不清。在本文中，我们提出了边缘-边界-纹理（EBT）损失，这是一种新颖的目标函数，它明确地将像素分为三类：边缘、边界和纹理，并为每一类分配一个独特的监督权重。这种三分式框架使模型能够进行更有结构化的学习，指导其关注边缘精度和上下文边界的定位。理论上证明了EBT损失泛化了WBCE损失，而后者成为一种极限情况。在多个基准测试中的广泛实验表明，从定量和感知角度来看，EBT损失优于传统的WBCE损失。此外，所有模型和数据集在整个研究中保持统一的超参数使用，并且对适度变化具有鲁棒性，这表明EBT损失需要最少的微调并且易于实际部署。
URL
https://arxiv.org/abs/2507.06569
