Active Learning with Ensembles for Image Classification
Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 1435-1435.
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.
Huan Liu, Amit Mandvikar, Patricia G. Foschi, and Kari Torkkola. 2003. Active Learning with Ensembles for Image Classification. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03. IJCAI, 1435–1435. https://ijcai.org/proceedings/2003/227
Liu, H., Mandvikar, A., Foschi, P. G., & Torkkola, K. (2003). Active Learning with Ensembles for Image Classification. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03 (pp. 1435–1435). IJCAI. https://ijcai.org/proceedings/2003/227
@inproceedings{ijcai2003p227,
title = {Active Learning with Ensembles for Image Classification},
author = {Liu, Huan and Mandvikar, Amit and Foschi, Patricia G. and Torkkola, Kari},
booktitle = {Proceedings of the Eighteenth International Joint Conference on
Artificial Intelligence, {IJCAI-03}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Georg Gottlob},
pages = {1435--1435},
year = {2003},
url = {https://ijcai.org/proceedings/2003/227},
}
TY - CPAPER TI - Active Learning with Ensembles for Image Classification AU - Liu, Huan AU - Mandvikar, Amit AU - Foschi, Patricia G. AU - Torkkola, Kari T2 - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03 PB - International Joint Conferences on Artificial Intelligence PY - 2003 SP - 1435 EP - 1435 UR - https://ijcai.org/proceedings/2003/227 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
