Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems

Abstract : Even years ago, Szeliski et al. published an influential study on energy minimization methods for Markov random fields (MRF). This study provided valuable insights in choosing the best optimization technique for certain classes of problems. While these insights remain generally useful today, the phenominal success of random field models means that the kinds of inference problems we solve have changed significantly. Specifically, the models today often include higher order interactions, flexible connectivity structures, large label-spaces of different cardinalities, or learned energy tables. To reflect these changes, we provide a modernized and enlarged study. We present an empirical comparison of 24 state-of-art techniques on a corpus of 2,300 energy minimization instances from 20 diverse computer vision applications. To ensure reproducibility, we evaluate all methods in the OpenGM2 framework and report extensive results regarding runtime and solution quality. Key insights from our study agree with the results of Szeliski et al. for the types of models they studied. However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

https://hal-enpc.archives-ouvertes.fr/hal-00865699
Contributeur : Nikos Komodakis <>
Soumis le : mardi 24 septembre 2013 - 23:11:53
Dernière modification le : mercredi 17 mars 2021 - 03:34:56

Identifiants

Citation

Joerg Kappes, Bjoern Andres, Fred Hamprecht, Christoph Schnörr, Sebastian Nowozin, et al.. A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems. IEEE Conference on Computer Vision and Pattern Recognition 2013, Jun 2013, Portland, United States. pp.1-8, ⟨10.1109/CVPR.2013.175⟩. ⟨hal-00865699⟩

Partager

Métriques

Consultations de la notice

8295