Inference by Learning: Speeding-up Graphical Model Optimization via a Coarse-to-Fine Cascade of Pruning Classifier.

This is the home page for the IbyL framework. This work was published at the NIPS2014 conference and is the result of the collaboration with N.Komodakis, S.Leprince, and J-P Avouac.

I presented this work at the NIPS conference in Montreal, CA, during the morning poster session of Tuesday, December 9, 2014.


We propose a general and versatile framework that significantly speeds-up graphical model optimization while maintaining an excellent solution accuracy. The proposed approach, refereed as Inference by Learning or in short as IbyL, relies on a multi-scale pruning scheme that progressively reduces the solution space by use of a coarse-to-fine cascade of learnt classifiers. We thoroughly experiment with classic computer vision related MRF problems, where our novel framework constantly yields a significant time speed-up (with respect to the most efficient inference methods) and obtains a more accurate solution than directly optimizing the MRF.

Useful Materials: