Multi-scale pseudo labeling for unsupervised deep edge detection

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Multi-scale pseudo labeling for unsupervised deep edge detection. / Zhou, Changsheng; Yuan, Chao; Wang, Hongxin; Li, Lei; Oehmcke, Stefan; Liu, Junmin; Peng, Jigen.

I: Knowledge-Based Systems, Bind 280, 111057, 2023.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Zhou, C, Yuan, C, Wang, H, Li, L, Oehmcke, S, Liu, J & Peng, J 2023, 'Multi-scale pseudo labeling for unsupervised deep edge detection', Knowledge-Based Systems, bind 280, 111057. https://doi.org/10.1016/j.knosys.2023.111057

APA

Zhou, C., Yuan, C., Wang, H., Li, L., Oehmcke, S., Liu, J., & Peng, J. (2023). Multi-scale pseudo labeling for unsupervised deep edge detection. Knowledge-Based Systems, 280, [111057]. https://doi.org/10.1016/j.knosys.2023.111057

Vancouver

Zhou C, Yuan C, Wang H, Li L, Oehmcke S, Liu J o.a. Multi-scale pseudo labeling for unsupervised deep edge detection. Knowledge-Based Systems. 2023;280. 111057. https://doi.org/10.1016/j.knosys.2023.111057

Author

Zhou, Changsheng ; Yuan, Chao ; Wang, Hongxin ; Li, Lei ; Oehmcke, Stefan ; Liu, Junmin ; Peng, Jigen. / Multi-scale pseudo labeling for unsupervised deep edge detection. I: Knowledge-Based Systems. 2023 ; Bind 280.

Bibtex

@article{4f90171350da443ea3eb840c217148c0,
title = "Multi-scale pseudo labeling for unsupervised deep edge detection",
abstract = "Deep learning currently rules edge detection. However, the impressive progress heavily relies on high-quality manually annotated labels which require a significant amount of labor and time. In this study, we propose a novel unsupervised learning framework for deep edge detection. It adopts a gradient-based method to generate scale-dependent pseudo edge maps, which match with the hierarchical structure of deep networks. It leverages both the representation learning capability of deep learning, and the simplicity of traditional methods. Experiments on three popular data sets show that the proposed method can suppress non-object edges and reduce the gap with its supervised counterpart due to the introduction of information of various scales and smoothing strategy.",
keywords = "Edge detection, Multi-scale modeling, Pseudo labeling, Unsupervised learning",
author = "Changsheng Zhou and Chao Yuan and Hongxin Wang and Lei Li and Stefan Oehmcke and Junmin Liu and Jigen Peng",
note = "Publisher Copyright: {\textcopyright} 2023 The Author(s)",
year = "2023",
doi = "10.1016/j.knosys.2023.111057",
language = "English",
volume = "280",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Multi-scale pseudo labeling for unsupervised deep edge detection

AU - Zhou, Changsheng

AU - Yuan, Chao

AU - Wang, Hongxin

AU - Li, Lei

AU - Oehmcke, Stefan

AU - Liu, Junmin

AU - Peng, Jigen

N1 - Publisher Copyright: © 2023 The Author(s)

PY - 2023

Y1 - 2023

N2 - Deep learning currently rules edge detection. However, the impressive progress heavily relies on high-quality manually annotated labels which require a significant amount of labor and time. In this study, we propose a novel unsupervised learning framework for deep edge detection. It adopts a gradient-based method to generate scale-dependent pseudo edge maps, which match with the hierarchical structure of deep networks. It leverages both the representation learning capability of deep learning, and the simplicity of traditional methods. Experiments on three popular data sets show that the proposed method can suppress non-object edges and reduce the gap with its supervised counterpart due to the introduction of information of various scales and smoothing strategy.

AB - Deep learning currently rules edge detection. However, the impressive progress heavily relies on high-quality manually annotated labels which require a significant amount of labor and time. In this study, we propose a novel unsupervised learning framework for deep edge detection. It adopts a gradient-based method to generate scale-dependent pseudo edge maps, which match with the hierarchical structure of deep networks. It leverages both the representation learning capability of deep learning, and the simplicity of traditional methods. Experiments on three popular data sets show that the proposed method can suppress non-object edges and reduce the gap with its supervised counterpart due to the introduction of information of various scales and smoothing strategy.

KW - Edge detection

KW - Multi-scale modeling

KW - Pseudo labeling

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=85174551668&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2023.111057

DO - 10.1016/j.knosys.2023.111057

M3 - Journal article

AN - SCOPUS:85174551668

VL - 280

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

M1 - 111057

ER -

ID: 372609481