Scale Learning in Scale-Equivariant Convolutional Networks

Mark Basting, Robert-Jan Bruintjes, Thaddäus Wiedemer, Thaddäus Wiedemer, Matthias Kümmerer, Matthias Bethge, Matthias Bethge, Jan van Gemert

2024

Abstract

Objects can take up an arbitrary number of pixels in an image: Objects come in different sizes, and, photographs of these objects may be taken at various distances to the camera. These pixel size variations are problematic for CNNs, causing them to learn separate filters for scaled variants of the same objects which prevents learning across scales. This is addressed by scale-equivariant approaches that share features across a set of pre-determined fixed internal scales. These works, however, give little information about how to best choose the internal scales when the underlying distribution of sizes, or scale distribution, in the dataset, is unknown. In this work we investigate learning the internal scales distribution in scale-equivariant CNNs, allowing them to adapt to unknown data scale distributions. We show that our method can learn the internal scales on various data scale distributions and can adapt the internal scales in current scale-equivariant approaches.

Paper Citation

in Harvard Style

Basting M., Bruintjes R., Wiedemer T., Kümmerer M., Bethge M. and van Gemert J. (2024). Scale Learning in Scale-Equivariant Convolutional Networks. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 567-574. DOI: 10.5220/0012379800003660

in Bibtex Style

@conference{visapp24,
author={Mark Basting and Robert-Jan Bruintjes and Thaddäus Wiedemer and Matthias Kümmerer and Matthias Bethge and Jan van Gemert},
title={Scale Learning in Scale-Equivariant Convolutional Networks},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={567-574},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012379800003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Scale Learning in Scale-Equivariant Convolutional Networks
SN - 978-989-758-679-8
AU - Basting M.
AU - Bruintjes R.
AU - Wiedemer T.
AU - Kümmerer M.
AU - Bethge M.
AU - van Gemert J.
PY - 2024
SP - 567
EP - 574
DO - 10.5220/0012379800003660
PB - SciTePress