We develop a new edge detection algorithm that addresses two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. Our proposed method, holistically-nested edge detection (HED), performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automatically learns rich hierarchical representations (guided by deep supervision on side responses) that are important in order to resolve the challenging ambiguity in edge and object boundary detection. We significantly advance the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.790) and the NYU Depth dataset (ODS F-score of 0.746), and do so with an improved speed (0.4 s per image) that is orders of magnitude faster than some CNN-based edge detection algorithms developed before HED. We also observe encouraging results on other boundary detection benchmark datasets such as Multicue and PASCAL-Context.

我们开发了一种新的边缘检测算法，解决了这个长期存在的视觉问题中的两个重要问题：（1）整体图像训练和预测；（2）多尺度，多层次的特征学习。我们提出的方法是整体嵌套边缘检测（HED），它通过利用完全卷积神经网络和深度监督网络的深度学习模型来执行图像到图像的预测。HED自动学习丰富的层次结构表示（在对副作用的深入监督指导下），这对于解决边缘和对象边界检测中的挑战性歧义非常重要。我们大大提高了BSDS500数据集（ODS F分数为0.790）和NYU深度数据集（ODS F分数为0.746）的最新技术，并以提高的速度进行了改进（0。每张图片4 s），比HED之前开发的某些基于CNN的边缘检测算法快几个数量级。我们还在其他边界检测基准数据集（例如Multicue和PASCAL-Context）上观察到令人鼓舞的结果。