Journal
INTERNATIONAL JOURNAL OF COMPUTER VISION
Volume 125, Issue 1-3, Pages 3-18Publisher
SPRINGER
DOI: 10.1007/s11263-017-1004-z
Keywords
Edge detection; Convolutional neural networks; Boundary detection; Multi-scale learning; Fusion; Deep learning
Categories
Funding
- NSF [NSF IIS-1618477IIS-1216528 (IIS-1360566), IIS-0844566 (IIS-1360568), NSF IIS-1618477]
- Northrop Grumman Contextual Robotics Grant
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available