Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization

Alexander Kirillov, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

Publikation: Beitrag in Buch/Bericht/KonferenzbandSonstiger Beitrag in Buch/Bericht/KonferenzbandBegutachtung


We consider the problem of jointly inferring the M-best diverse labelings for a binary (high-order) submodular energy of a graphical model. Recently, it was shown that this problem can be solved to a global optimum, for many practically interesting diversity measures. It was noted that the labelings are, so-called, nested. This nestedness property also holds for labelings of a class of parametric submodu- lar minimization problems, where different values of the global parameter γ give rise to different solutions. The popular example of the parametric submodular minimization is the monotonic parametric max-flow problem, which is also widely used for computing multiple labelings. As the main contribution of this work we establish a close relationship between diversity with submodular energies and the parametric submodular minimization. In particular, the joint M-best diverse labelings can be obtained by running a non-parametric submodular minimization (in the special case - max-flow) solver for M different values of γ in parallel, for certain diversity measures. Importantly, the values for γ can be computed in a closed form in advance, prior to any optimization. These theoretical results suggest two simple yet efficient algorithms for the joint M-best diverse problem, which outperform competitors in terms of runtime and quality of results. In particular, as we show in the paper, the new methods compute the exact M -best diverse labelings faster than a popular method of Batra et al., which in some sense only obtains approximate solutions.
TitelAdvances in Neural Information Processing Systems 29
Redakteure/-innenD. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, R. Garnett
Herausgeber (Verlag)Curran Associates, Inc
PublikationsstatusVeröffentlicht - 2016

Dieses zitieren