Active Learning in Social Context for Image Classification

Elisavet Chatzilari, Spiros Nikolopoulos, Yiannis Kompatsiaris, Josef Kittler

2014

Abstract

Motivated by the widespread adoption of social networks and the abundant availability of user-generated multimedia content, our purpose in this work is to investigate how the known principles of active learning for image classification fit in this newly developed context. The process of active learning can be fully automated in this social context by replacing the human oracle with the user tagged images obtained from social networks. However, the noisy nature of user-contributed tags adds further complexity to the problem of sample selection since, apart from their informativeness, our confidence about their actual content should be also maximized. The contribution of this work is on proposing a probabilistic approach for jointly maximizing the two aforementioned quantities with a view to automate the process of active learning. Experimental results show the superiority of the proposed method against various baselines and verify the assumption that significant performance improvement cannot be achieved unless we jointly consider the samples’ informativeness and the oracle’s confidence.

Paper Citation

in Harvard Style

Chatzilari E., Nikolopoulos S., Kompatsiaris Y. and Kittler J. (2014). Active Learning in Social Context for Image Classification . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 76-85. DOI: 10.5220/0004686400760085

in Bibtex Style

@conference{visapp14,
author={Elisavet Chatzilari and Spiros Nikolopoulos and Yiannis Kompatsiaris and Josef Kittler},
title={Active Learning in Social Context for Image Classification},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={76-85},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004686400760085},
isbn={978-989-758-004-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Active Learning in Social Context for Image Classification
SN - 978-989-758-004-8
AU - Chatzilari E.
AU - Nikolopoulos S.
AU - Kompatsiaris Y.
AU - Kittler J.
PY - 2014
SP - 76
EP - 85
DO - 10.5220/0004686400760085