Skip to yearly menu bar Skip to main content


Poster

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

Maurice Weiler · Wouter Boomsma · Mario Geiger · Max Welling · Taco Cohen

Room 210 #45

Keywords: [ Classification ] [ CNN Architectures ]


Abstract:

We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equivariant convolutions to map between such representations. These SE(3)-equivariant convolutions utilize kernels which are parameterized as a linear combination of a complete steerable kernel basis, which is derived analytically in this paper. We prove that equivariant convolutions are the most general equivariant linear maps between fields over R^3. Our experimental results confirm the effectiveness of 3D Steerable CNNs for the problem of amino acid propensity prediction and protein structure classification, both of which have inherent SE(3) symmetry.

Live content is unavailable. Log in and register to view live content