Holistically-Nested Edge Detection
This addresses the long-standing vision problem of edge detection for computer vision applications, offering significant improvements in accuracy and speed.
The paper tackled edge detection by proposing a holistically-nested method that leverages deep learning for multi-scale feature learning, achieving state-of-the-art F-scores of 0.782 on BSD500 and 0.746 on NYU Depth with a speed of 0.4 seconds per image.
We develop a new edge detection algorithm that tackles 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 approach the human ability resolve the challenging ambiguity in edge and object boundary detection. We significantly advance the state-of-the-art on the BSD500 dataset (ODS F-score of .782) and the NYU Depth dataset (ODS F-score of .746), and do so with an improved speed (0.4 second per image) that is orders of magnitude faster than some recent CNN-based edge detection algorithms.