Research map / Architectures and efficiency / CNN design
Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add a spherical scattering network before the hybrid spherical CNN | Hybrid spherical CNN · CMB Gaussianity classification (L=1024) | accuracy: 53.1\% -> 95.3\% | Helped |
| Add a spherical scattering network before the hybrid spherical CNN | Hybrid spherical CNN · Spherical MNIST at varying resolutions | classification accuracy | Helped |
| Use multi-resolution wavelet coefficients (ablation) | Spherical scattering network · Wavelet transform experiments | equivariance and accuracy | No clear effect |
| Increase the baseline hybrid model's first-layer channels from K1=20 to K1=21 (ablation) | Hybrid spherical CNN without scattering · Spherical MNIST at varying resolutions | classification accuracy | No clear effect |
Closest papers by meaning
- Efficient Generalized Spherical CNNs (ICLR 2021 · similarity 0.91)
- Spherical CNNs (ICLR 2018 · similarity 0.91)
- Scaling Spherical CNNs (ICML 2023 · similarity 0.90)
- Spin-Weighted Spherical CNNs (NeurIPS 2020 · similarity 0.90)
- Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions (ICLR 2023 · similarity 0.90)
- Attention on the Sphere (NeurIPS 2025 · similarity 0.86)
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.