Active learning with ensembles for image classification

Huan Liu, A. Mandvikar, P. Foschi, K. Torkkola

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In many real-world tasks of image classification, limited amounts of labeled data are available to train automatic classifiers. Consequently, extensive human expert involvement is required for verification. A novel solution is presented that makes use of active learning combined with an ensemble of classifiers for each class. The result is a significant reduction in required expert involvement for uncertain image region classification.

Original languageEnglish (US)
Title of host publicationIJCAI International Joint Conference on Artificial Intelligence
Pages1435-1436
Number of pages2
StatePublished - 2003
Event18th International Joint Conference on Artificial Intelligence, IJCAI 2003 - Acapulco, Mexico
Duration: Aug 9 2003Aug 15 2003

Other

Other18th International Joint Conference on Artificial Intelligence, IJCAI 2003
CountryMexico
CityAcapulco
Period8/9/038/15/03

Fingerprint

Image classification
Classifiers
Problem-Based Learning

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Liu, H., Mandvikar, A., Foschi, P., & Torkkola, K. (2003). Active learning with ensembles for image classification. In IJCAI International Joint Conference on Artificial Intelligence (pp. 1435-1436)

Active learning with ensembles for image classification. / Liu, Huan; Mandvikar, A.; Foschi, P.; Torkkola, K.

IJCAI International Joint Conference on Artificial Intelligence. 2003. p. 1435-1436.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, H, Mandvikar, A, Foschi, P & Torkkola, K 2003, Active learning with ensembles for image classification. in IJCAI International Joint Conference on Artificial Intelligence. pp. 1435-1436, 18th International Joint Conference on Artificial Intelligence, IJCAI 2003, Acapulco, Mexico, 8/9/03.
Liu H, Mandvikar A, Foschi P, Torkkola K. Active learning with ensembles for image classification. In IJCAI International Joint Conference on Artificial Intelligence. 2003. p. 1435-1436
Liu, Huan ; Mandvikar, A. ; Foschi, P. ; Torkkola, K. / Active learning with ensembles for image classification. IJCAI International Joint Conference on Artificial Intelligence. 2003. pp. 1435-1436
@inproceedings{fd4a22ff78eb4358b5895d6621dd13d4,
title = "Active learning with ensembles for image classification",
abstract = "In many real-world tasks of image classification, limited amounts of labeled data are available to train automatic classifiers. Consequently, extensive human expert involvement is required for verification. A novel solution is presented that makes use of active learning combined with an ensemble of classifiers for each class. The result is a significant reduction in required expert involvement for uncertain image region classification.",
author = "Huan Liu and A. Mandvikar and P. Foschi and K. Torkkola",
year = "2003",
language = "English (US)",
pages = "1435--1436",
booktitle = "IJCAI International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - Active learning with ensembles for image classification

AU - Liu, Huan

AU - Mandvikar, A.

AU - Foschi, P.

AU - Torkkola, K.

PY - 2003

Y1 - 2003

N2 - In many real-world tasks of image classification, limited amounts of labeled data are available to train automatic classifiers. Consequently, extensive human expert involvement is required for verification. A novel solution is presented that makes use of active learning combined with an ensemble of classifiers for each class. The result is a significant reduction in required expert involvement for uncertain image region classification.

AB - In many real-world tasks of image classification, limited amounts of labeled data are available to train automatic classifiers. Consequently, extensive human expert involvement is required for verification. A novel solution is presented that makes use of active learning combined with an ensemble of classifiers for each class. The result is a significant reduction in required expert involvement for uncertain image region classification.

UR - http://www.scopus.com/inward/record.url?scp=47649103195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47649103195&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:47649103195

SP - 1435

EP - 1436

BT - IJCAI International Joint Conference on Artificial Intelligence

ER -