Publications

Authors:

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

Title:

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

Year:

2014

Type of item:

Articolo in Rivista

Tipologia ANVUR:

Articolo su rivista

Language:

Inglese

Format:

A Stampa

Referee:

Sì

Name of journal:

COMPUTER GRAPHICS FORUM

ISSN of journal:

0167-7055

N° Volume:

33

Number or Folder:

5

Page numbers:

127-136

Keyword:

Bag of Words; shape descriptors; Metric learning

Short description of contents:

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.

Product ID:

82436

Handle IRIS:

11562/763369

Deposited On:

July 22, 2014

Last Modified:

November 15, 2022

Bibliographic citation:

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