TY - GEN
T1 - Holistically-nested edge detection
AU - Xie, Saining
AU - Tu, Zhuowen
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/2/17
Y1 - 2015/2/17
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84973859794&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973859794&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2015.164
DO - 10.1109/ICCV.2015.164
M3 - Conference contribution
AN - SCOPUS:84973859794
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 1395
EP - 1403
BT - 2015 International Conference on Computer Vision, ICCV 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Computer Vision, ICCV 2015
Y2 - 11 December 2015 through 18 December 2015
ER -