Land Cover Classification with Superpixels and Jaccard Index Post-Optimization

CVPRW 2018 pp. 280-284

doi:10.1109/CVPRW.2018.00053 /cvprw/2018/davydow2018cvprw-land/

Abstract

In this work, we consider the land cover classification task of the DeepGlobe Challenge. This task features the largest available labeled dataset for satellite imagery segmentation. We propose an approach to this problem where standard neural network image classification models are augmented by superpixel extraction and postprocessing that aims to directly optimize the average Jaccard index.

CVPRW Semantic Scholar

Cite

Text

Davydow and Nikolenko. "Land Cover Classification with Superpixels and Jaccard Index Post-Optimization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00053

Markdown

[Davydow and Nikolenko. "Land Cover Classification with Superpixels and Jaccard Index Post-Optimization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/davydow2018cvprw-land/) doi:10.1109/CVPRW.2018.00053

BibTeX

@inproceedings{davydow2018cvprw-land,
  title     = {{Land Cover Classification with Superpixels and Jaccard Index Post-Optimization}},
  author    = {Davydow, Alex and Nikolenko, Sergey I.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {280-284},
  doi       = {10.1109/CVPRW.2018.00053},
  url       = {https://mlanthology.org/cvprw/2018/davydow2018cvprw-land/}
}