Residual Inception Skip Network for Binary Segmentation

CVPRW 2018 pp. 216-219

doi:10.1109/CVPRW.2018.00037 /cvprw/2018/doshi2018cvprw-residual/

Abstract

This paper summarizes our approach to the Deep Globe Road Extraction challenge 2018. In this challenge we are tasked to find road networks from satellite images. First, we explain our U-Net type baseline model for the challenge. Second, we explain a new architecture that takes in the lessons from some of the popular approaches that we call Residual Inception Skip Net. Finally, we outline our cyclic learning rate based ensembling approach which improved the overall single model performance and the final solution for submission. Our final model increases the IoU by 3 points over the baseline.

CVPRW Semantic Scholar

Cite

Text

Doshi. "Residual Inception Skip Network for Binary Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00037

Markdown

[Doshi. "Residual Inception Skip Network for Binary Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/doshi2018cvprw-residual/) doi:10.1109/CVPRW.2018.00037

BibTeX

@inproceedings{doshi2018cvprw-residual,
  title     = {{Residual Inception Skip Network for Binary Segmentation}},
  author    = {Doshi, Jigar},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {216-219},
  doi       = {10.1109/CVPRW.2018.00037},
  url       = {https://mlanthology.org/cvprw/2018/doshi2018cvprw-residual/}
}