Importance Order Ranking for Texture Extraction: A More Efficient Pooling Operator Than Max Pooling?

S. Ibarra, V. Vigneron, J.-Ph. Conge, H. Maaref

2022

Abstract

Much of convolutional neural network (CNN)’s success lies in translation invariance. The other part resides in the fact that thanks to a judicious choice of architecture, the network is able to make decisions taking into account the whole image. This work provides an alternative way to extend the pooling function, we named rank-order pooling, capable of extracting texture descriptors from images. The rank-order pooling layers are non parametric, independent of the geometric arrangement or sizes of the image regions, and can therefore better tolerate rotations. Rank-order pooling functions produce images capable of emphasizing low/high frequencies, contours, etc. We shows rank-order pooling leads to CNN models which can optimally exploit information from their receptive field.

Download


Paper Citation


in Harvard Style

Ibarra S., Vigneron V., Conge J. and Maaref H. (2022). Importance Order Ranking for Texture Extraction: A More Efficient Pooling Operator Than Max Pooling?. In Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-585-2, pages 585-594. DOI: 10.5220/0011142200003271


in Bibtex Style

@conference{icinco22,
author={S. Ibarra and V. Vigneron and J.-Ph. Conge and H. Maaref},
title={Importance Order Ranking for Texture Extraction: A More Efficient Pooling Operator Than Max Pooling?},
booktitle={Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2022},
pages={585-594},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011142200003271},
isbn={978-989-758-585-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - Importance Order Ranking for Texture Extraction: A More Efficient Pooling Operator Than Max Pooling?
SN - 978-989-758-585-2
AU - Ibarra S.
AU - Vigneron V.
AU - Conge J.
AU - Maaref H.
PY - 2022
SP - 585
EP - 594
DO - 10.5220/0011142200003271