From Label Maps to Label Strokes: Semantic Segmentation for Street Scenes from Incomplete Training Data

Abstract

This paper proposes a novel image parsing framework to solve the semantic pixel labeling problem from only label strokes. Our framework is based on a network of voters, each of which aggregates both a self voting vector and a neighborhood context. The voters are parameterized using sparse convex coding. To efficiently learn the parameters, we propose a regularized energy function that propagates label information in the training data while taking into account of context interaction and a backward composition algorithm for efficient gradient computation. Our framework is capable of handling label strokes and is scalable to a code book of millions of bases. Our experiment results show the effectiveness of our framework on both synthetic examples and real world applications.

Cite

Text

Zhu et al. "From Label Maps to Label Strokes: Semantic Segmentation for Street Scenes from Incomplete Training Data." IEEE/CVF International Conference on Computer Vision Workshops, 2013. doi:10.1109/ICCVW.2013.129

Markdown

[Zhu et al. "From Label Maps to Label Strokes: Semantic Segmentation for Street Scenes from Incomplete Training Data." IEEE/CVF International Conference on Computer Vision Workshops, 2013.](https://mlanthology.org/iccvw/2013/zhu2013iccvw-label/) doi:10.1109/ICCVW.2013.129

BibTeX

@inproceedings{zhu2013iccvw-label,
  title     = {{From Label Maps to Label Strokes: Semantic Segmentation for Street Scenes from Incomplete Training Data}},
  author    = {Zhu, Shengqi and Yang, Yiqing and Zhang, Li},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2013},
  pages     = {468-475},
  doi       = {10.1109/ICCVW.2013.129},
  url       = {https://mlanthology.org/iccvw/2013/zhu2013iccvw-label/}
}