OpenAlex · Aktualisierung stündlich · Letzte Aktualisierung: 25.04.2026, 18:05

Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.

Holistically-Nested Edge Detection

2015·3.100 Zitationen
Volltext beim Verlag öffnen

3.100

Zitationen

2

Autoren

2015

Jahr

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.

Ähnliche Arbeiten

Autoren

Institutionen

Themen

Advanced Neural Network ApplicationsImage and Object Detection TechniquesMedical Image Segmentation Techniques
Volltext beim Verlag öffnen