Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Edixhoven, Tom"'
In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries. We focus on 2D rotations and reflections and investigate the impact of broken equivariance on network perfor
Externí odkaz:
http://arxiv.org/abs/2308.11316
