AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network

Risi Kondor, Zhen Lin, Shubhendu Trivedi

NeurIPS 2018 · Architectures and efficiency › CNN design · approach: Steerable rotation-equivariant CNNs · 36 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use fully Fourier-space Clebsch–Gordan layers instead of the Spherical CNN architectureSpherical image classification · Rotated MNIST on the Sphere NR/NRaccuracy: 95.59 -> 96.4Improved
Use fully Fourier-space Clebsch–Gordan layers instead of the Spherical CNN architectureSpherical image classification · Rotated MNIST on the Sphere NR/Raccuracy: 94.62 -> 96Improved
Use fully Fourier-space Clebsch–Gordan layers instead of the Spherical CNN architectureSpherical image classification · Rotated MNIST on the Sphere R/Raccuracy: 93.4 -> 96.6Improved
Use fully Fourier-space Clebsch–Gordan layers instead of the Spherical CNN architectureQM7 atomization energy prediction · QM7RMSE: 8.47 -> 7.97Improved
Use fully Fourier-space Clebsch–Gordan layers instead of the Spherical CNN architectureQM7 atomization energy prediction · QM7RMSE: 5.96 -> 7.97Hurt
Use fully Fourier-space Clebsch–Gordan layers instead of task-specialized shape models3D shape recognition · SHREC17P@N: 0.814 -> 0.707Hurt
Use fully Fourier-space Clebsch–Gordan layers instead of task-specialized shape models3D shape recognition · SHREC17R@N: 0.769 -> 0.722Hurt
Use fully Fourier-space Clebsch–Gordan layers instead of task-specialized shape models3D shape recognition · SHREC17F1@N: 0.719 -> 0.701Hurt
Use fully Fourier-space Clebsch–Gordan layers instead of task-specialized shape models3D shape recognition · SHREC17mAP: 0.696 -> 0.683Hurt
Use fully Fourier-space Clebsch–Gordan layers instead of task-specialized shape models3D shape recognition · SHREC17NDCG: 0.783 -> 0.756Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy