Automatically selecting inference algorithms for discrete energy minimisation

Henderson, P. and Ferrari, V. (2016) Automatically selecting inference algorithms for discrete energy minimisation. In: Leibe, B., Matas, J., Sebe, N. and Welling, M. (eds.) Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V. Series: Lecture notes in computer science (9909). Springer: Cham, pp. 235-252. ISBN 9783319464534 (doi: 10.1007/978-3-319-46454-1_15)

Full text not currently available from Enlighten.

Abstract

Minimisation of discrete energies defined over factors is an important problem in computer vision, and a vast number of MAP inference algorithms have been proposed. Different inference algorithms perform better on factor graph models (GMs) from different underlying problem classes, and in general it is difficult to know which algorithm will yield the lowest energy for a given GM. To mitigate this difficulty, survey papers [1–3] advise the practitioner on what algorithms perform well on what classes of models. We take the next step forward, and present a technique to automatically select the best inference algorithm for an input GM. We validate our method experimentally on an extended version of the OpenGM2 benchmark [3], containing a diverse set of vision problems. On average, our method selects an inference algorithm yielding labellings with 96 % of variables the same as the best available algorithm.

Item Type:Book Sections
Status:Published
Glasgow Author(s) Enlighten ID:Henderson, Dr Paul
Authors: Henderson, P., and Ferrari, V.
College/School:College of Science and Engineering > School of Computing Science
Publisher:Springer
ISBN:9783319464534
Published Online:16 September 2016

University Staff: Request a correction | Enlighten Editors: Update this record