Learning Semantic Attributes via a Common Latent Space

Ziad Al-Halah, Tobias Gehrig, Rainer Stiefelhagen

2014

Abstract

Semantic attributes represent an adequate knowledge that can be easily transferred to other domains where lack of information and training samples exist. However, in the classical object recognition case, where training data is abundant, attribute-based recognition usually results in poor performance compared to methods that used image features directly. We introduce a generic framework that boosts the performance of semantic attributes considerably in traditional classification and knowledge transfer tasks, such as zero-shot learning. It incorporates the discriminative power of the visual features and the semantic meaning of the attributes by learning a common latent space that joins both spaces. We also specifically account for the presence of attribute correlations in the source dataset to generalize more efficiently across domains. Our evaluation of the proposed approach on standard public datasets shows that it is not only simple and computationally efficient but also performs remarkably better than the common direct attribute model.

Paper Citation

in Harvard Style

Al-Halah Z., Gehrig T. and Stiefelhagen R. (2014). Learning Semantic Attributes via a Common Latent Space . 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 48-55. DOI: 10.5220/0004681500480055

in Bibtex Style

@conference{visapp14,
author={Ziad Al-Halah and Tobias Gehrig and Rainer Stiefelhagen},
title={Learning Semantic Attributes via a Common Latent Space},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={48-55},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004681500480055},
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 - Learning Semantic Attributes via a Common Latent Space
SN - 978-989-758-004-8
AU - Al-Halah Z.
AU - Gehrig T.
AU - Stiefelhagen R.
PY - 2014
SP - 48
EP - 55
DO - 10.5220/0004681500480055