8079

Nonmetric Priors for Continuous Multilabel Optimization

Evgeny Strekalovskiy, Claudia Nieuwenhuis, Daniel Cremers
Technical University Munich, Germany
European Conference on Computer Vision (ECCV), 2012

@inProceedings{Strekalovskiy-et-al-eccv12,

   author={E. Strekalovskiy and C. Nieuwenhuis and D. Cremers},

   title={Nonmetric Priors for Continuous Multilabel Optimization},

   booktitle={eccv},

   year={2012},

   address={Firenze, Italy},

   month={oct},

   topic={Convex Relaxation Methods},

   keywords={convex-relaxation}

}

Download Download (PDF)   View View   Source Source   

606

views

We propose a novel convex prior for multilabel optimization which allows to impose arbitrary distances between labels. Only symmetry, d(i; j) >= 0 and d(i; i) = 0 are required. In contrast to previous grid based approaches for the nonmetric case, the proposed prior is formulated in the continuous setting avoiding grid artifacts. In particular, the model is easy to implement, provides a convex relaxation for the Mumford-Shah functional and yields comparable or superior results on the MSRC segmentation database comparing to metric or grid based approaches.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: