In this paper we promote the idea of using pixel-based models not only for low level vision, but also to extract high level symbolic representations. We use a deep architecture which has the distinctive property of relying on computational units that incorporate classic computer vision invariances and, especially, the scale invariance. The learning algorithm that is proposed, which is based on information theory principles, develops the parameters of the computational units and, at the same time, makes it possible to detect the optimal scale for each pixel. We give experimental evidence of the mechanism of feature extraction at the first level of the hierarchy, which is very much related to SIFT-like features. The comparison shows clearly that, whenever we can rely on the massive availability of training data, the proposed model leads to better performances with respect to SIFT.

Gori, M., Melacci, S., Lippi, M., Maggini, M. (2012). Information Theoretic Learning for Pixel-Based Visual Agents. In Computer Vision - ECCV 2012 (pp.864-875). Springer Verlag [10.1007/978-3-642-33783-3_62].

Information Theoretic Learning for Pixel-Based Visual Agents

GORI, MARCO;MELACCI, STEFANO;LIPPI, MARCO;MAGGINI, MARCO
2012-01-01

Abstract

In this paper we promote the idea of using pixel-based models not only for low level vision, but also to extract high level symbolic representations. We use a deep architecture which has the distinctive property of relying on computational units that incorporate classic computer vision invariances and, especially, the scale invariance. The learning algorithm that is proposed, which is based on information theory principles, develops the parameters of the computational units and, at the same time, makes it possible to detect the optimal scale for each pixel. We give experimental evidence of the mechanism of feature extraction at the first level of the hierarchy, which is very much related to SIFT-like features. The comparison shows clearly that, whenever we can rely on the massive availability of training data, the proposed model leads to better performances with respect to SIFT.
978-3-642-33782-6
Gori, M., Melacci, S., Lippi, M., Maggini, M. (2012). Information Theoretic Learning for Pixel-Based Visual Agents. In Computer Vision - ECCV 2012 (pp.864-875). Springer Verlag [10.1007/978-3-642-33783-3_62].
File in questo prodotto:
File Dimensione Formato  
2012 - ECCV.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.88 MB
Formato Adobe PDF
1.88 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/40602
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo