Inferring M-best diverse labelings in a single one

TitleInferring M-best diverse labelings in a single one
Publication TypeConference Paper
Year of Publication2015
AuthorsKirillov, A, Savchynskyy, B, Schlesinger, D, Vetrov, D, Rother, C
Conference NameProceedings of the IEEE International Conference on Computer Vision
ISBN Number9781467383912

We consider the task of finding M-best diverse solutions in a graphical model. In a previous work by Batra et al. an algorithmic approach for finding such solutions was proposed, and its usefulness was shown in numerous applications. Contrary to previous work we propose a novel formulation of the problem in form of a single energy minimization problem in a specially constructed graphical model. We show that the method of Batra et al. can be considered as a greedy approximate algorithm for our model, whereas we introduce an efficient specialized optimization technique for it, based on alpha-expansion. We evaluate our method on two application scenarios, interactive and semantic image segmentation, with binary and multiple labels. In both cases we achieve considerably better error rates than state-of-the art diversity methods. Furthermore, we empirically discover that in the binary label case we were able to reach global optimality for all test instances.

Citation KeyKirillov2015a