Paper Info
Title
Holistically-Nested Edge Detection.
Abstract
We develop a new edge detection algorithm that addresses two critical issues in this long-standing vision problem: (1) holistic image training, and (2) multi-scale feature learning. Our proposed method, holistically-nested edge detection (HED), turns pixel-wise edge classification into 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 crucially important in order to approach the human ability to 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 0.782) and the NYU Depth dataset (ODS F-score of 0.746), and do so with an improved speed (0.4 second per image) that is orders of magnitude faster than recent CNN-based edge detection algorithms.
Year
DOI
Venue
2015
10.1007/s11263-017-1004-z
International Journal of Computer Vision
Keywords
DocType
Volume
Edge detection,Convolutional neural networks,Boundary detection,Multi-scale learning,Fusion,Deep learning
Journal
125
Issue
ISSN
Citations 
1-3
0920-5691
140
PageRank 
References 
Authors
3.28
35
2
Search Limit
100140
Name
Order
Citations
PageRank
Saining Xie123112.45
Zhuowen Tu23663215.79