Iterative residual network for structured edge detection

Yupei Wang, Xin Zhao, Kaiqi Huang

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)
Plum Print visual indicator of research metrics
  • Citations
    • Citation Indexes: 7
  • Captures
    • Readers: 4
see details

摘要

Edge detection aims to find visually distinctive edges or boundaries in input images. Edge detection has made significant progress with the help of deep Convolutional Networks (ConvNet). Most ConvNet-based edge detectors predict each pixel independently and ignore the inherent correlations between pixels. However, structured cues in input images are critical to learn a good edge detector. To this end, we propose a novel Iterative Residual Holistically-nested Edge Detection (IRHED) network. IRHED incorporates multi-scale features from the hierarchy of the network, and learns to iteratively refine the output boundary map in a deeply supervised manner. In this way, global structural cues, such as object shape, are learned implicitly, thus edges can be effectively distinguished. Extensive experiments demonstrate that IRHED achieves state-of-the-art results on the widely used BSDS500 dataset. We also show the benefit of structured edge map for higher-level task, such as object proposal generation.

源语言英语
主期刊名2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
出版商IEEE Computer Society
4183-4187
页数5
ISBN(电子版)9781479970612
DOI
出版状态已出版 - 29 8月 2018
已对外发布
活动25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, 希腊
期限: 7 10月 201810 10月 2018

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
ISSN(印刷版)1522-4880

会议

会议25th IEEE International Conference on Image Processing, ICIP 2018
国家/地区希腊
Athens
时期7/10/1810/10/18

指纹

探究 'Iterative residual network for structured edge detection' 的科研主题。它们共同构成独一无二的指纹。

引用此

Wang, Y., Zhao, X., & Huang, K. (2018). Iterative residual network for structured edge detection. 在 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (页码 4183-4187). 文章 8466129 (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8466129