ML Anthology

Deepstrip: High-Resolution Boundary Refinement

Peng Zhou, Brian Price, Scott Cohen, Gregg Wilensky, Larry S. Davis
CVPR 2020
doi:10.1109/CVPR42600.2020.01057 /cvpr/2020/zhou2020cvpr-deepstrip/

Abstract

In this paper, we target refining the boundaries in high resolution images given low resolution masks. For memory and computation efficiency, we propose to convert the regions of interest into strip images and compute a boundary prediction in the strip domain. To detect the target boundary, we present a framework with two prediction layers. First, all potential boundaries are predicted as an initial prediction and then a selection layer is used to pick the target boundary and smooth the result. To encourage accurate prediction, a loss which measures the boundary distance in strip domain is introduced. In addition, we enforce a matching consistency and C0 continuity regularization to the network to reduce false alarms. Extensive experiments on both public and a newly created high resolution dataset strongly validate our approach.

PDF CVPR Semantic Scholar

Cite

Text

Zhou et al. "Deepstrip: High-Resolution Boundary Refinement." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.01057

Markdown

[Zhou et al. "Deepstrip: High-Resolution Boundary Refinement." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/zhou2020cvpr-deepstrip/) doi:10.1109/CVPR42600.2020.01057

BibTeX

@inproceedings{zhou2020cvpr-deepstrip,
  title     = {{Deepstrip: High-Resolution Boundary Refinement}},
  author    = {Zhou, Peng and Price, Brian and Cohen, Scott and Wilensky, Gregg and Davis, Larry S.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.01057},
  url       = {https://mlanthology.org/cvpr/2020/zhou2020cvpr-deepstrip/}
}