Equivariance versus Augmentation for Spherical Images
Paper in proceeding, 2022

We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with an increasing amount of data augmentation. The chosen architectures can be considered baseline references for the respective design paradigms. Our models are trained and evaluated on single or multiple items from the MNIST or FashionMNIST dataset projected onto the sphere. For the task of image classification, which is inherently rotationally invariant, we find that by considerably increasing the amount of data augmentation and the size of the networks, it is possible for the standard CNNs to reach at least the same performance as the equivariant network. In contrast, for the inherently equivariant task of semantic segmentation, the non-equivariant networks are consistently outperformed by the equivariant networks with significantly fewer parameters. We also analyze and compare the inference latency and training times of the different networks, enabling detailed tradeoff considerations between equivariant architectures and data augmentation for practical problems. The equivariant spherical networks used in the experiments are available at https://github.com/JanEGerken/sem_seg_s2cnn.

Author

Jan Gerken

Technische Universität Berlin

Chalmers, Mathematical Sciences, Algebra and geometry

BIFOLD - Berlin Institute for the Foundations of Learning and Data

Oscar Carlsson

Chalmers, Mathematical Sciences, Algebra and geometry

Hampus Linander

University of Gothenburg

Fredrik Ohlsson

Umeå University

Christoffer Petersson

Zenseact AB

Chalmers, Mathematical Sciences, Algebra and geometry

Daniel Persson

Chalmers, Mathematical Sciences, Algebra and geometry

Proceedings of Machine Learning Research

26403498 (eISSN)

Vol. 162 7404-7421

39th International Conference on Machine Learning, ICML 2022
Baltimore, USA,

Subject Categories

Computer Engineering

Communication Systems

Bioinformatics (Computational Biology)

Mathematical Analysis

More information

Latest update

1/15/2024