M-Best-Diverse Labelings for Submodular Energies and Beyond

Part of Advances in Neural Information Processing Systems 28 (NIPS 2015)

Bibtex Metadata Paper Reviews Supplemental


Alexander Kirillov, Dmytro Shlezinger, Dmitry P. Vetrov, Carsten Rother, Bogdan Savchynskyy


We consider the problem of finding M best diverse solutions of energy minimization problems for graphical models. Contrary to the sequential method of Batra et al., which greedily finds one solution after another, we infer all $M$ solutions jointly. It was shown recently that such jointly inferred labelings not only have smaller total energy but also qualitatively outperform the sequentially obtained ones. The only obstacle for using this new technique is the complexity of the corresponding inference problem, since it is considerably slower algorithm than the method of Batra et al. In this work we show that the joint inference of $M$ best diverse solutions can be formulated as a submodular energy minimization if the original MAP-inference problem is submodular, hence fast inference techniques can be used. In addition to the theoretical results we provide practical algorithms that outperform the current state-of-the art and can be used in both submodular and non-submodular case.