Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators. Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators. In this paper, we propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations. Specifically, we first convert the deterministic label space into a learnable Gaussian distribution, whose variance measures the degree of ambiguity among different annotations. Then we regard the learned variance as the estimated uncertainty of the predicted edge maps, and pixels with higher uncertainty are likely to be hard samples for edge detection. Therefore we design an adaptive weighting loss to emphasize the learning from those pixels with high uncertainty, which helps the network to gradually concentrate on the important pixels. UAED can be combined with various encoder-decoder backbones, and the extensive experiments demonstrate that UAED achieves superior performance consistently across multiple edge detection benchmarks. The source code is available at \url{https://github.com/ZhouCX117/UAED}

翻译：基于深度学习的边缘检测器高度依赖于像素级标签，而这些标签通常由多位标注者提供。现有方法采用简单的投票过程融合多份标注，忽视了边缘固有的模糊性及标注者的标注偏差。本文提出一种新颖的不确定性感知边缘检测器（UAED），利用不确定性来探究多样化标注的主观性与模糊性。具体而言，我们首先将确定性标签空间转化为可学习的高斯分布，其方差衡量不同标注之间的模糊程度。随后，我们将学习到的方差视为预测边缘图的估计不确定性，高不确定性的像素很可能是边缘检测中的困难样本。因此，我们设计了一种自适应加权损失函数，以加强对高不确定性像素的学习，帮助网络逐步聚焦于重要像素。UAED可搭配多种编码器-解码器骨干网络，大量实验表明，UAED在多个边缘检测基准上持续取得优越性能。源代码见\url{https://github.com/ZhouCX117/UAED}。