Research map / Architectures and efficiency / CNN design
Achieving Rotational Invariance with Bessel-Convolutional Neural Networks
Valentin Delchevalerie, Adrien Bibal, Benoit Frenay, Alexandre Mayer
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use Bessel convolutions instead of group convolutions | B-CNN · Outex feature map equivariance | feature map difference (%): 10.64% -> 1.77% | Improved |
| use Bessel convolutions instead of standard convolutions | B-CNN · Outex feature map equivariance | feature map difference (%): 5.73% -> 1.77% | Improved |
| add random rotation data augmentation to training (ablation) | all models (B-CNN, G-CNN, CNN) · MNIST, Outex, brain MRI | test accuracy | Improved |
| B-CNN vs G-CNN without data augmentation | B-CNN · MNIST | test accuracy | Improved |
| B-CNN vs G-CNN without data augmentation | B-CNN · Outex | test accuracy | No clear effect |
| B-CNN vs G-CNN with data augmentation | B-CNN · Outex | test accuracy: less than 5% accuracy | Improved |
| low-data setting, 75% of training set removed | B-CNN vs G-CNN · Outex low data | test accuracy: a little bit less than 15% | Improved |
Closest papers by meaning
- RRL: Regional Rotate Layer in Convolutional Neural Networks (AAAI 2022 · similarity 0.87)
- Exploiting Cyclic Symmetry in Convolutional Neural Networks (ICML 2016 · similarity 0.86)
- Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network (NeurIPS 2018 · similarity 0.86)
- Spin-Weighted Spherical CNNs (NeurIPS 2020 · similarity 0.85)
- Rotation Equivariant Vector Field Networks (ICCV 2017 · similarity 0.85)
- On Making $SE(2)$-Invariant Networks Optimal (NeurIPS 2026 · similarity 0.84)
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.
