Exploiting Learned Symmetries in Group Equivariant Convolutions

Conference paper (2021)

Authors

A. Lengyel Pattern Recognition and Bioinformatics -

J.C. van Gemert Pattern Recognition and Bioinformatics -

Research Group

Pattern Recognition and Bioinformatics () (TU Delft)

Group equivariant convolutions Depth-wise separable convolutions Efficient deep learning

To reference this document use:

http://resolver.tudelft.nl/uuid:47818acb-da1f-4335-9ea9-36c56fbf087e

More Info

expand_more

Published Date

2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

Abstract

Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost. We investigate the filter parameters learned by GConvs and find certain conditions under which they become highly redundant. We show that GConvs can be efficiently decomposed into depthwise separable convolutions while preserving equivariance properties and demonstrate improved performance and data efficiency on two datasets. All code is publicly available at github.com/Attila94/SepGrouPy.

Files

Exploiting_Learned_Symmetries_... (pdf)

(pdf | 1.05 Mb)

Unknown license

Download not available