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

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...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 33; no. 5; pp. 127 - 136
Main Authors: Litman, Roee, Bronstein, Alex, Bronstein, Michael, Castellani, Umberto
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.08.2014
Subjects:
Analysis
Artificial intelligence
Clustering
Coding
Computer graphics
Computer programming
Dictionaries
Image retrieval
Learning
Optimization
Retrieval
Studies
Texts
Vector quantization
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ark:/67375/WNG-KX45LWHF-8
istex:268207A2F34DE46B771C812EE41B0B27DA1F0B82
ArticleID:CGF12438
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.12438