Timezone: »

 
Poster
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
Maurice Weiler · Wouter Boomsma · Mario Geiger · Max Welling · Taco S Cohen

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #45
in Tue Poster Session A »

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.

Keywords: Classification · CNN Architectures

Author Information

Maurice Weiler (University of Amsterdam)
Wouter Boomsma (University of Copenhagen)
Mario Geiger (EPFL)
Max Welling (University of Amsterdam / Qualcomm AI Research)
Taco S Cohen (University of Amsterdam)

More from the Same Authors