Hallucinating Saliency Maps for Fine-grained Image Classification for Limited Data Domains

Carola Figueroa-Flores, Carola Figueroa-Flores, Bogdan Raducanu, David Berga, Joost van de Weijer

Abstract

It has been shown that saliency maps can be used to improve the performance of object recognition systems, especially on datasets that have only limited training data. However, a drawback of such an approach is that it requires a pre-trained saliency network. In the current paper, we propose an approach which does not require explicit saliency maps to improve image classification, but they are learned implicitely, during the training of an end-to-end image classification task. We show that our approach obtains similar results as the case when the saliency maps are provided explicitely. We validate our method on several datasets for fine-grained classification tasks (Flowers, Birds and Cars), and show that especially for domains with limited data the proposed method significantly improves the results.

Download


Paper Citation


in Harvard Style

Figueroa-Flores C., Raducanu B., Berga D. and van de Weijer J. (2021). Hallucinating Saliency Maps for Fine-grained Image Classification for Limited Data Domains.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 163-171. DOI: 10.5220/0010299501630171


in Bibtex Style

@conference{visapp21,
author={Carola Figueroa-Flores and Bogdan Raducanu and David Berga and Joost van de Weijer},
title={Hallucinating Saliency Maps for Fine-grained Image Classification for Limited Data Domains},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={163-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010299501630171},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Hallucinating Saliency Maps for Fine-grained Image Classification for Limited Data Domains
SN - 978-989-758-488-6
AU - Figueroa-Flores C.
AU - Raducanu B.
AU - Berga D.
AU - van de Weijer J.
PY - 2021
SP - 163
EP - 171
DO - 10.5220/0010299501630171