Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds

By Stefan C. Schonsheck, Bin Dong, Rongjie Lai. 2018

24 citations recorded by the source corpus.

Convolution has been playing a prominent role in various applications in science and engineering for many years. It is the most important operation in convolutional neural networks. There has been a recent growth of interests of research in generalizing convolutions on curved domains such as manifolds and graphs. However, existing approaches cannot preserve all the desirable properties of Euclidean convolutions, namely compactly supported filters, directionality, transferability across different manifolds. In this paper we develop a new generalization of the convolution operation, referred to as parallel transport convolution (PTC), on Riemannian manifolds and their discrete counterparts. PTC is designed based on the parallel transportation which is able to translate information along a manifold and to intrinsically preserve directionality. PTC allows for the construction of compactly supported filters and is also robust to manifold deformations. This enables us to preform wavelet-like operations and to define deep convolutional neural networks on curved domains.

Subfields: Building and Construction, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

Max Welling

In Computer Vision and Pattern Recognition

Citations in the corpus

Gauge Equivariant Convolutional Networks and the Icosahedral CNN (2019, background): “Instead of symmetries, one can move the filter by parallel transport (Schonsheck et al., 2018), but as shown in Fig.”