Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks. (arXiv:2210.16646v1 [cs.CV])

Equivariant networks have been adopted in many 3-D learning areas. Here we
identify a fundamental limitation of these networks: their ambiguity to
symmetries. Equivariant networks cannot complete symmetry-dependent tasks like
segmenting a left-right symmetric object into its left and right sides. We
tackle this problem by adding components that resolve symmetry ambiguities
while preserving rotational equivariance. We present OAVNN: Orientation Aware
Vector Neuron Network, an extension of the Vector Neuron Network. OAVNN is a
rotation equivariant network that is robust …

arxiv breaking networks neural networks symmetry