Supervised Learning of Bag-of-features Shape Descriptors Using Sparse Coding
Loading...
Date
2014
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley and Sons Ltd.
Abstract
We present a method for supervised learning of shape descriptors for shape retrieval applications. Many contentbased 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 taskspecific objective that promotes invariance desired in the specific application. We show significant performance improvement on several standard shape retrieval benchmarks.
Description
@article{10.1111:cgf.12438,
journal = {Computer Graphics Forum},
title = {{Supervised Learning of Bag-of-features Shape Descriptors Using Sparse Coding}},
author = {Litman, Roee and Bronstein, Alex and Bronstein, Michael and Castellani, Umberto},
year = {2014},
publisher = {The Eurographics Association and John Wiley and Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.12438}
}