Title
Deep Crisp Boundaries: From Boundaries to Higher-level Tasks.
Abstract
Edge detection has made significant progress with the help of deep convolutional networks (ConvNet). These ConvNet-based edge detectors have approached human level performance on standard benchmarks. We provide a systematical study of these detectors' outputs. We show that the detection results did not accurately localize edge pixels, which can be adversarial for tasks that require crisp edge inpu...
Year
DOI
Venue
2019
10.1109/TIP.2018.2874279
IEEE Transactions on Image Processing
Keywords
DocType
Volume
Image edge detection,Detectors,Task analysis,Proposals,Optical imaging,Semantics,Standards
Journal
28
Issue
ISSN
Citations 
3
1057-7149
8
PageRank 
References 
Authors
0.50
33
4
Name
Order
Citations
PageRank
Yupei Wang1131.97
Xin Zhao213917.21
Yin Li379735.85
Kaiqi Huang41931118.74