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

Weiler, M, Geiger, M, Welling, M, Boomsma, W & Cohen, T 2018, 3D steerable CNNs: Learning rotationally equivariant features in volumetric data. in Proceedings of the 32nd International Conference on Neural Information Processing Systems. derc edn, vol. 2018, NIPS Proceedings, Advances in Neural Information Processing Systems, vol. 31, pp. 10381-10392, 32nd Annual Conference on Neural Information Processing Systems, Montreal, Canada, 02/12/2018.

APA

Weiler, M., Geiger, M., Welling, M., Boomsma, W., & Cohen, T. (2018). 3D steerable CNNs: Learning rotationally equivariant features in volumetric data. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (derc ed., Vol. 2018, pp. 10381-10392). NIPS Proceedings. Advances in Neural Information Processing Systems Vol. 31

Vancouver

Weiler M, Geiger M, Welling M, Boomsma W, Cohen T. 3D steerable CNNs: Learning rotationally equivariant features in volumetric data. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. derc ed. Vol. 2018. NIPS Proceedings. 2018. p. 10381-10392. (Advances in Neural Information Processing Systems, Vol. 31).

Author

Weiler, Maurice ; Geiger, Mario ; Welling, Max ; Boomsma, Wouter ; Cohen, Taco. / 3D steerable CNNs : Learning rotationally equivariant features in volumetric data. Proceedings of the 32nd International Conference on Neural Information Processing Systems. Vol. 2018 derc. ed. NIPS Proceedings, 2018. pp. 10381-10392 (Advances in Neural Information Processing Systems, Vol. 31).

Bibtex

@inproceedings{38dcfaf2b371412cb00e4d441f8b8544,
title = "3D steerable CNNs: Learning rotationally equivariant features in volumetric data",
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.",
author = "Maurice Weiler and Mario Geiger and Max Welling and Wouter Boomsma and Taco Cohen",
year = "2018",
language = "English",
volume = "2018",
series = "Advances in Neural Information Processing Systems",
publisher = "NIPS Proceedings",
pages = "10381--10392",
booktitle = "Proceedings of the 32nd International Conference on Neural Information Processing Systems",
edition = "derc",
note = "32nd Annual Conference on Neural Information Processing Systems, NeurIPS ; Conference date: 02-12-2018 Through 08-12-2018",
url = "https://nips.cc/Conferences/2018",

}

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