Spherical CNNs

Preprint English OPEN
Cohen, Taco S. ; Geiger, Mario ; Koehler, Jonas ; Welling, Max (2018)
  • Subject: Statistics - Machine Learning | Computer Science - Learning
    acm: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION

Convolutional Neural Networks (CNNs) have become the method of choice for learning problems involving 2D planar images. However, a number of problems of recent interest have created a demand for models that can analyze spherical images. Examples include omnidirectional vision for drones, robots, and autonomous cars, molecular regression problems, and global weather and climate modelling. A naive application of convolutional networks to a planar projection of the spherical signal is destined to fail, because the space-varying distortions introduced by such a projection will make translational weight sharing ineffective. In this paper we introduce the building blocks for constructing spherical CNNs. We propose a definition for the spherical cross-correlation that is both expressive and rotation-equivariant. The spherical correlation satisfies a generalized Fourier theorem, which allows us to compute it efficiently using a generalized (non-commutative) Fast Fourier Transform (FFT) algorithm. We demonstrate the computational efficiency, numerical accuracy, and effectiveness of spherical CNNs applied to 3D model recognition and atomization energy regression.
  • References (38)
    38 references, page 1 of 4

    L. C. Blum and J.-L. Reymond. 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. J. Am. Chem. Soc., 131:8732, 2009.

    W. Boomsma and J. Frellsen. Spherical convolutions and their application in molecular modelling. In I Guyon, U V Luxburg, S Bengio, H Wallach, R Fergus, S Vishwanathan, and R Garnett, editors, Advances in Neural Information Processing Systems 30, pages 3436-3446. Curran Associates, Inc., 2017.

    A.X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su, et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015.

    G.S. Chirikjian and A.B. Kyatkin. Engineering Applications of Noncommutative Harmonic Analysis. CRC Press, 1 edition, may 2001. ISBN 9781420041767.

    T.S. Cohen and M. Welling. Group equivariant convolutional networks. In Proceedings of The 33rd International Conference on Machine Learning (ICML), volume 48, pages 2990-2999, 2016.

    T.S. Cohen and M. Welling. Steerable CNNs. In ICLR, 2017.

    T.S. Cohen, M. Geiger, J. Koehler, and M. Welling. Convolutional networks for spherical signals. In ICML Workshop on Principled Approaches to Deep Learning, 2017.

    S. Dieleman, K. W. Willett, and J. Dambre. Rotation-invariant convolutional neural networks for galaxy morphology prediction. Monthly Notices of the Royal Astronomical Society, 450(2), 2015.

    S. Dieleman, J. De Fauw, and K. Kavukcuoglu. Exploiting Cyclic Symmetry in Convolutional Neural Networks. In International Conference on Machine Learning (ICML), 2016.

    J.B. Drake, P.H. Worley, and E.F. D'Azevedo. Algorithm 888: Spherical harmonic transform algorithms. ACM Trans. Math. Softw., 35(3):23:1-23:23, 2008. doi: 10.1145/1391989.1404581.

  • Related Research Results (1)
  • Metrics
    No metrics available
Share - Bookmark