CaltechAUTHORS
  A Caltech Library Service

Learning Object Categories From Internet Image Searches

Fergus, Rob and Li, Fei-Fei and Perona, Pietro and Zisserman, Andrew (2010) Learning Object Categories From Internet Image Searches. Proceedings of the IEEE, 98 (8). pp. 1453-1466. ISSN 0018-9219. https://resolver.caltech.edu/CaltechAUTHORS:20101116-100053561

[img]
Preview
PDF - Published Version
See Usage Policy.

2892Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20101116-100053561

Abstract

In this paper, we describe a simple approach to learning models of visual object categories from images gathered from Internet image search engines. The images for a given keyword are typically highly variable, with a large fraction being unrelated to the query term, and thus pose a challenging environment from which to learn. By training our models directly from Internet images, we remove the need to laboriously compile training data sets, required by most other recognition approaches-this opens up the possibility of learning object category models “on-the-fly.” We describe two simple approaches, derived from the probabilistic latent semantic analysis (pLSA) technique for text document analysis, that can be used to automatically learn object models from these data. We show two applications of the learned model: first, to rerank the images returned by the search engine, thus improving the quality of the search engine; and second, to recognize objects in other image data sets.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/JPROC.2010.2048990DOIUNSPECIFIED
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5483225PublisherUNSPECIFIED
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2010 IEEE. Manuscript received April 7, 2009; revised September 23, 2009; accepted March 22, 2010. Date of publication June 10, 2010; date of current version July 21, 2010. This work was supported by the Caltech Center for Neuromorphic Systems Engineering (CNSE), the U.K. Engineering and Physical Sciences Research Council (EPSRC), European Union NOE PASCAL, the European Research Council (ERC) under Grant VisRec, and the U.S. Office of Naval Research (ONR) Multidisciplinary University Research Initiative (MURI) under Grants N00014-06-1-0734 and N00014-07-1-0182. The authors would like to thank David Forsyth.
Funders:
Funding AgencyGrant Number
Caltech Center for Neuromorphic Systems Engineering (CNSE)UNSPECIFIED
Engineering and Physical Sciences Research Council (EPSRC)UNSPECIFIED
European Union NOE PASCALUNSPECIFIED
European Research Council (ERC)VisRec
Office of Naval Research (ONR) Multidisciplinary University Research Initiative (MURI)N00014-06-1-0734
Office of Naval Research (ONR) Multidisciplinary University Research Initiative (MURI)N00014-07-1-0182
Subject Keywords:Internet image search engines; learning; object categories; recognition; unsupervised
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number11430135
Issue or Number:8
Record Number:CaltechAUTHORS:20101116-100053561
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20101116-100053561
Official Citation:Fergus, R.; Li Fei-Fei; Perona, P.; Zisserman, A.; , "Learning Object Categories From Internet Image Searches," Proceedings of the IEEE , vol.98, no.8, pp.1453-1466, Aug. 2010 doi: 10.1109/JPROC.2010.2048990 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5483225&isnumber=5512706
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:20829
Collection:CaltechAUTHORS
Deposited By: Jason Perez
Deposited On:16 Nov 2010 23:02
Last Modified:03 Oct 2019 02:15

Repository Staff Only: item control page