ECCV 2012 - LNCS 7572-7578 and 7583-7585

Unsupervised Classemes

Claudio Cusano¹, Riccardo Satta², and Simone Santini³

¹Department of Informatics, Systems and Communication (DISCo), Università degli Studi di Milano-Bicocca, Viale Sarca 336, 20126, Milano, Italy

²Department of Electrical and Electronic Engineering, Università di Cagliari, Italy

³Escuela Politécnica Superior, Universidad Autónoma de Madrid, Spain

Abstract. In this paper we present a new model of semantic features that, unlike previously presented methods, does not rely on the presence of a labeled training data base, as the creation of the feature extraction function is done in an unsupervised manner.

We test these features on an unsupervised classification (clustering) task, and show that they outperform primitive (low-level) features, and that have performance comparable to that of supervised semantic features, which are much more expensive to determine relying on the presence of a labeled training set to train the feature extraction function.

LNCS 7585, p. 406 ff.

Full article in PDF | BibTeX