Linear Discriminant Analysis for Zero-shot Learning Image Retrieval

Sovann EN, Frédéric Jurie, Stéphane Nicolas, Caroline Petitjean, Laurent Heutte

2015

Abstract

This paper introduces a new distance function for comparing images in the context of content-based image retrieval. Given a query and a large dataset to be searched, the system has to provide the user – as efficiently as possible – with a list of images ranked according to their distance to the query. Because of computational issues, traditional image search systems are generally based on conventional distance function such as the Euclidian distance or the dot product, avoiding the use of any training data nor expensive online metric learning algorithms. The drawback is that, in this case, the system can hardly cope with the variability of image contents. This paper proposes a simple yet efficient zero-shot learning algorithm that can learn a query-adapted distance function from a single image (the query) or from a few images (e.g. some user-selected images in a relevance feedback iteration), hence improving the quality of the retrieved images. This allows our system to work with any object categories without requiring any training data, and is hence more applicable in real world use cases. More interestingly, our system can learn the metric on the fly, at almost no cost, and the cost of the ranking function is as low as the dot product distance. By allowing the system to learn to rank the images, significantly and consistently improved results (over the conventional approaches) have been observed on the Oxford5k, Paris6k and Holiday1k datasets.

Paper Citation

in Harvard Style

EN S., Jurie F., Nicolas S., Petitjean C. and Heutte L. (2015). Linear Discriminant Analysis for Zero-shot Learning Image Retrieval . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 70-77. DOI: 10.5220/0005300200700077

in Bibtex Style

@conference{visapp15,
author={Sovann EN and Frédéric Jurie and Stéphane Nicolas and Caroline Petitjean and Laurent Heutte},
title={Linear Discriminant Analysis for Zero-shot Learning Image Retrieval},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={70-77},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005300200700077},
isbn={978-989-758-090-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Linear Discriminant Analysis for Zero-shot Learning Image Retrieval
SN - 978-989-758-090-1
AU - EN S.
AU - Jurie F.
AU - Nicolas S.
AU - Petitjean C.
AU - Heutte L.
PY - 2015
SP - 70
EP - 77
DO - 10.5220/0005300200700077