Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Symmetry and Geometry in Neural Representations (NeurReps)

Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks

Sidhika Balachandar · Adrien Poulenard · Congyue Deng · Leonidas Guibas

Keywords: [ point cloud analysis ] [ planar symmetry ] [ 3-D learning ] [ O(3) equivariance ]


Abstract:

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 Deng et al. (2021). OAVNN is a rotation equivariant network that is robust to planar symmetric inputs. Our network consists of three key components. 1) We introduce an algorithm to calculate symmetry detecting features. 2) We create a symmetry-sensitive orientation aware linear layer. 3) We construct an attention mechanism that relates directional information across points. We evaluate the network using left-right segmentation and find that the network quickly obtains accurate segmentations. We hope this work motivates investigations on the expressivity of equivariant networks on symmetric objects.

Chat is not available.