Pubblicazioni

Autori:

Roee, Litman; Alex, Bronstein; Michael, Bronstein; Castellani, Umberto

Titolo:

Supervised learning of bag-of-features shape descriptors using sparse coding

Anno:

2014

Tipologia prodotto:

Articolo in Rivista

Tipologia ANVUR:

Articolo su rivista

Lingua:

Inglese

Formato:

A Stampa

Referee:

Sì

Nome rivista:

COMPUTER GRAPHICS FORUM

ISSN Rivista:

0167-7055

N° Volume:

33

Numero o Fascicolo:

5

Intervallo pagine:

127-136

Parole chiave:

Bag of Words; shape descriptors; Metric learning

Breve descrizione dei contenuti:

We present a method for supervised learning of shape descriptors for shape retrieval applications. Many content-based shape retrieval approaches follow the bag-of-features (BoF) paradigm commonly used in text and image retrieval by first computing local shape descriptors, and then representing them in a ‘geometric dictionary’ using vector quantization. A major drawback of such approaches is that the dictionary is constructed in an unsupervised manner using clustering, unaware of the last stage of the process pooling of the local descriptors into a BoF, and comparison of the latter using some metric). In this paper, we replace the clustering with dictionary learning where every atom acts as a feature, followed by sparse coding and pooling to get the final BoF descriptor. Both the dictionary and the sparse codes can be learned in the supervised regime via bi-level optimization using a task-specific objective that promotes invariance desired in the specific application. We show significant performance improvement on several standard shape retrieval benchmarks.

Id prodotto:

82436

Handle IRIS:

11562/763369

depositato il:

22 luglio 2014

ultima modifica:

15 novembre 2022

Citazione bibliografica:

Roee, Litman; Alex, Bronstein; Michael, Bronstein; Castellani, Umberto, Supervised learning of bag-of-features shape descriptors using sparse coding «COMPUTER GRAPHICS FORUM» , vol. 33 , n. 5 , 2014 , pp. 127-136

Consulta la scheda completa presente nel repository istituzionale della Ricerca di Ateneo