3D steerable CNNs: Learning rotationally equivariant features in volumetric data
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
3D steerable CNNs : Learning rotationally equivariant features in volumetric data. / Weiler, Maurice; Geiger, Mario; Welling, Max; Boomsma, Wouter; Cohen, Taco.
Proceedings of the 32nd International Conference on Neural Information Processing Systems. Vol. 2018 derc. ed. NIPS Proceedings, 2018. p. 10381-10392 (Advances in Neural Information Processing Systems, Vol. 31).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - 3D steerable CNNs
T2 - 32nd Annual Conference on Neural Information Processing Systems
AU - Weiler, Maurice
AU - Geiger, Mario
AU - Welling, Max
AU - Boomsma, Wouter
AU - Cohen, Taco
N1 - Conference code: 32
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
UR - http://www.mendeley.com/research/3d-steerable-cnns-learning-rotationally-equivariant-features-volumetric-data
UR - http://www.mendeley.com/research/3d-steerable-cnns-learning-rotationally-equivariant-features-volumetric-data
M3 - Article in proceedings
VL - 2018
T3 - Advances in Neural Information Processing Systems
SP - 10381
EP - 10392
BT - Proceedings of the 32nd International Conference on Neural Information Processing Systems
PB - NIPS Proceedings
Y2 - 2 December 2018 through 8 December 2018
ER -
ID: 236511653