Iterated Lifting for Robust Cost Optimization

Christopher Zach and Guillaume Bourmaud

Abstract

Optimization of latent model parameters using robust formulations usually creates a large number of local minima due to the quasi-convex shape of the underlying robust kernel. Lifting the robust kernel, i.e. embedding the problem into a higher-dimensional space, leads to significantly better local minima in a range of 3D computer vision problems (e.g. [10, 11, 12]). In this work we propose to iterate this lifting construction to obtain a more gradual lifting scheme for a given target kernel. Thus, a robust kernel is not directly lifted against the (non-robust) quadratic kernel, but initially against a different, less robust kernel. This process is iterated until the quadratic kernel is reached to allow utilization of efficient non-linear least-squares solvers.

Session

Posters

Files

Paper (PDF)
Supplementary (PDF)

DOI

10.5244/C.31.86
https://dx.doi.org/10.5244/C.31.86

Citation

Bibtex

            @inproceedings{BMVC2017_86,
                title={Iterated Lifting for Robust Cost Optimization},
                author={Christopher Zach and Guillaume Bourmaud},
                year={2017},
                month={September},
                pages={86.1-86.11},
                articleno={86},
                numpages={11},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.86},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.86}
            }