Steerable CNNs

Abstract

It has long been recognized that the invariance and equivariance properties of a representation are critically important for success in many vision tasks. In this paper we present Steerable Convolutional Neural Networks, an efficient and flexible class of equivariant convolutional networks. We show that steerable CNNs achieve state of the art results on the… (More)

Topics

6 Figures and Tables

Cite this paper

@article{Cohen2016SteerableC, title={Steerable CNNs}, author={Taco Cohen and Max Welling}, journal={CoRR}, year={2016}, volume={abs/1612.08498} }