ML Anthology

RSRN: Rich Side-Output Residual Network for Medial Axis Detection

Chang Liu, Wei Ke, Jianbin Jiao, Qixiang Ye
ICCVW 2017 pp. 1739-1743
doi:10.1109/ICCVW.2017.204 /iccvw/2017/liu2017iccvw-rsrn/

Abstract

In this paper, we propose a Rich Side-output Residual Network (RSRN) for medial axis detection for the ICCV 2017 workshop challenge on detecting symmetry in the wild. RSRN uses the rich features of fully convolutional network by hierarchically fusing side-outputs in a deep-to-shallow manner to decrease the residual between the detection result and the ground-truth, which refines the detection result hierarchically. Experimental results show that the proposed RSRN improves the performance compared with baseline on both SKLARGE and BMAX500 datasets.

ICCVW Semantic Scholar

Cite

Text

Liu et al. "RSRN: Rich Side-Output Residual Network for Medial Axis Detection." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.204

Markdown

[Liu et al. "RSRN: Rich Side-Output Residual Network for Medial Axis Detection." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/liu2017iccvw-rsrn/) doi:10.1109/ICCVW.2017.204

BibTeX

@inproceedings{liu2017iccvw-rsrn,
  title     = {{RSRN: Rich Side-Output Residual Network for Medial Axis Detection}},
  author    = {Liu, Chang and Ke, Wei and Jiao, Jianbin and Ye, Qixiang},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {1739-1743},
  doi       = {10.1109/ICCVW.2017.204},
  url       = {https://mlanthology.org/iccvw/2017/liu2017iccvw-rsrn/}
}