Laude E, Lange JH, Schuepfer J, Domokos C, Leal-Taixe L, Schmidt FR, Andres B, Cremers D (2018)
Publication Type: Conference contribution
Publication year: 2018
Publisher: IEEE Computer Society
Pages Range: 1614-1624
Conference Proceedings Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Event location: Salt Lake City, UT, USA
ISBN: 9781538664209
This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier. The considered task is posed as a joint optimization problem in the continuous classifier parameters and the discrete label variables. In contrast to prior approaches such as convex relaxations, we propose an advantageous decoupling of the objective function into discrete and continuous subproblems and a novel, efficient optimization method related to ADMM. This approach preserves integrality of the discrete label variables and guarantees global convergence to a critical point. We demonstrate the advantages of our approach in several experiments including video object segmentation on the DAVIS data set and interactive image segmentation.
APA:
Laude, E., Lange, J.-H., Schuepfer, J., Domokos, C., Leal-Taixe, L., Schmidt, F.R.,... Cremers, D. (2018). Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 1614-1624). Salt Lake City, UT, USA: IEEE Computer Society.
MLA:
Laude, Emanuel, et al. "Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs." Proceedings of the 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA IEEE Computer Society, 2018. 1614-1624.
BibTeX: Download