loading
Papers

Research.Publish.Connect.

Paper

Authors: Javier Jorge ; Jesús Vieco ; Roberto Paredes ; Joan Andreu Sanchez and José Miguel Benedí

Affiliation: Universitat Politècnica de València, Spain

ISBN: 978-989-758-290-5

Keyword(s): Generative Models, Data Augmentation, Variational Autoencoder.

Abstract: Since the beginning of Neural Networks, different mechanisms have been required to provide a sufficient number of examples to avoid overfitting. Data augmentation, the most common one, is focused on the generation of new instances performing different distortions in the real samples. Usually, these transformations are problem-dependent, and they result in a synthetic set of, likely, unseen examples. In this work, we have studied a generative model, based on the paradigm of encoder-decoder, that works directly in the data space, that is, with images. This model encodes the input in a latent space where different transformations will be applied. After completing this, we can reconstruct the latent vectors to get new samples. We have analysed various procedures according to the distortions that we could carry out, as well as the effectiveness of this process to improve the accuracy of different classification systems. To do this, we could use both the latent space and the original space after reconstructing the altered version of these vectors. Our results have shown that using this pipeline (encoding-altering-decoding) helps the generalisation of the classifiers that have been selected. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.227.249.234

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Jorge, J.; Vieco, J.; Paredes, R.; Sanchez, J. and Benedí, J. (2018). Empirical Evaluation of Variational Autoencoders for Data Augmentation.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-290-5, pages 96-104. DOI: 10.5220/0006618600960104

@conference{visapp18,
author={Javier Jorge. and Jesús Vieco. and Roberto Paredes. and Joan Andreu Sanchez. and José Miguel Benedí.},
title={Empirical Evaluation of Variational Autoencoders for Data Augmentation},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2018},
pages={96-104},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006618600960104},
isbn={978-989-758-290-5},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Empirical Evaluation of Variational Autoencoders for Data Augmentation
SN - 978-989-758-290-5
AU - Jorge, J.
AU - Vieco, J.
AU - Paredes, R.
AU - Sanchez, J.
AU - Benedí, J.
PY - 2018
SP - 96
EP - 104
DO - 10.5220/0006618600960104

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.