Unsupervised Feature Learning using Self-organizing Maps

Marco Vanetti, Ignazio Gallo, Angelo Nodari

2013

Abstract

In recent years a great amount of research has focused on algorithms that learn features from unlabeled data. In this work we propose a model based on the Self-Organizing Map (SOM) neural network to learn features useful for the problem of automatic natural images classification. In particular we use the SOM model to learn single-layer features from the extremely challenging CIFAR-10 dataset, containing 60.000 tiny labeled natural images, and subsequently use these features with a pyramidal histogram encoding to train a linear SVM classifier. Despite the large number of images, the proposed feature learning method requires only few minutes on an entry-level system, however we show that a supervised classifier trained with learned features provides significantly better results than using raw pixels values or other handcrafted features designed specifically for image classification. Moreover, exploiting the topological property of the SOM neural network, it is possible to reduce the number of features and speed up the supervised training process combining topologically close neurons, without repeating the feature learning process.

Paper Citation

in Harvard Style

Vanetti M., Gallo I. and Nodari A. (2013). Unsupervised Feature Learning using Self-organizing Maps . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 596-601. DOI: 10.5220/0004210305960601

in Bibtex Style

@conference{visapp13,
author={Marco Vanetti and Ignazio Gallo and Angelo Nodari},
title={Unsupervised Feature Learning using Self-organizing Maps},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={596-601},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004210305960601},
isbn={978-989-8565-47-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Unsupervised Feature Learning using Self-organizing Maps
SN - 978-989-8565-47-1
AU - Vanetti M.
AU - Gallo I.
AU - Nodari A.
PY - 2013
SP - 596
EP - 601
DO - 10.5220/0004210305960601