Poster
Free energy score space
Alessandro Perina · Marco Cristani · Umberto Castellani · Vittorio Murino · Nebojsa Jojic

Mon Dec 7th 07:00 -- 11:59 PM @ None #None

Score functions induced by generative models extract fixed-dimension feature vectors from different-length data observations by subsuming the process of data generation, projecting them in highly informative spaces called score spaces. In this way, standard discriminative classifiers are proved to achieve higher performances than a solely generative or discriminative approach. In this paper, we present a novel score space that exploits the free energy associated to a generative model through a score function. This function aims at capturing both the uncertainty of the model learning and ``local compliance of data observations with respect to the generative process. Theoretical justifications and convincing comparative classification results on various generative models prove the goodness of the proposed strategy.

Author Information

Alessandro Perina (Microsoft Research)
Marco Cristani
Umberto Castellani
Vittorio Murino (Istituto Italiano di Tecnologia)
Nebojsa Jojic (Microsoft Research)

More from the Same Authors