Holistically-Nested Edge Detection

Saining Xie, Zhuowen Tu

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Pages (from-to)3-18
Number of pages16
JournalInternational Journal of Computer Vision
Issue number1-3
StatePublished - Dec 1 2017


  • Boundary detection
  • Convolutional neural networks
  • Deep learning
  • Edge detection
  • Fusion
  • Multi-scale learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Holistically-Nested Edge Detection'. Together they form a unique fingerprint.

Cite this