Fine-Grained Retrieval with Autoencoders

Tiziano Portenier, Qiyang Hu, Paolo Favaro, Matthias Zwicker

2018

Abstract

In this paper we develop a representation for fine-grained retrieval. Given a query, we want to retrieve data items of the same class, and, in addition, rank these items according to intra-class similarity. In our training data we assume partial knowledge: class labels are available, but the intra-class attributes are not. To compensate for this knowledge gap we propose using an autoencoder, which can be trained to produce features both with and without labels. Our main hypothesis is that network architectures that incorporate an autoencoder can learn features that meaningfully cluster data based on the intra-class variability. We propose and compare different architectures to construct our features, including a Siamese autoencoder (SAE), a classifying autoencoder (CAE) and a separate classifier-autoencoder (SCA). We find that these architectures indeed improve fine-grained retrieval compared to features trained purely in a supervised fashion for classification. We perform experiments on four datasets, and observe that the SCA generally outperforms the other two. In particular, we obtain state of the art performance on fine-grained sketch retrieval.

Paper Citation

in Harvard Style

Portenier T., Hu Q., Favaro P. and Zwicker M. (2018). Fine-Grained Retrieval with Autoencoders. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 85-95. DOI: 10.5220/0006602100850095

in Bibtex Style

@conference{visapp18,
author={Tiziano Portenier and Qiyang Hu and Paolo Favaro and Matthias Zwicker},
title={Fine-Grained Retrieval with Autoencoders},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={85-95},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006602100850095},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Fine-Grained Retrieval with Autoencoders
SN - 978-989-758-290-5
AU - Portenier T.
AU - Hu Q.
AU - Favaro P.
AU - Zwicker M.
PY - 2018
SP - 85
EP - 95
DO - 10.5220/0006602100850095
PB - SciTePress