The Likelihood-Ratio Test and Efficient Robust Estimation

ICCV 2015

doi:10.1109/ICCV.2015.263 /iccv/2015/cohen2015iccv-likelihoodratio/

Abstract

Robust estimation of model parameters in the presence of outliers is a key problem in computer vision. RANSAC inspired techniques are widely used in this context, although their application might be limited due to the need of a priori knowledge on the inlier noise level. We propose a new approach for jointly optimizing over model parameters and the inlier noise level based on the likelihood ratio test. This allows control over the type I error incurred. We also propose an early bailout strategy for efficiency. Tests on both synthetic and real data show that our method outperforms the state-of-the-art in a fraction of the time.

PDF ICCV Semantic Scholar

Cite

Text

Cohen and Zach. "The Likelihood-Ratio Test and Efficient Robust Estimation." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.263

Markdown

[Cohen and Zach. "The Likelihood-Ratio Test and Efficient Robust Estimation." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/cohen2015iccv-likelihoodratio/) doi:10.1109/ICCV.2015.263

BibTeX

@inproceedings{cohen2015iccv-likelihoodratio,
  title     = {{The Likelihood-Ratio Test and Efficient Robust Estimation}},
  author    = {Cohen, Andrea and Zach, Christopher},
  booktitle = {International Conference on Computer Vision},
  year      = {2015},
  doi       = {10.1109/ICCV.2015.263},
  url       = {https://mlanthology.org/iccv/2015/cohen2015iccv-likelihoodratio/}
}