Research map / Architectures and efficiency / CNN design
Deep Scale-spaces: Equivariance Over Scale
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 |
|---|---|---|---|
| use scale-equivariant correlations (S-DenseNet) instead of standard DenseNet | DenseNet · Patch Camelyon | accuracy: 87.0 -> 88.1 | Helped |
| use scale-equivariant ResNet instead of channel-matched ResNet | ResNet · Cityscapes | mAP: 49.99 -> 63.53 | Helped |
| use scale-equivariant ResNet instead of parameter-matched ResNet | ResNet · Cityscapes | mAP: 45.66 -> 63.53 | Helped |
| add multiscale interaction (scale-dimension 2 filters) (ablation) | S-ResNet · Cityscapes | mAP: 64.78 -> 63.53 | Hurt |
| scale-equivariant model vs rotation-equivariant model | S-DenseNet · Patch Camelyon | accuracy: 89.8 -> 88.1 | Hurt |
Closest papers by meaning
- Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution (ICLR 2023 · similarity 0.90)
- Scale-Equivariant Steerable Networks (ICLR 2020 · similarity 0.90)
- Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space (ICLR 2024 · similarity 0.88)
- Probing Equivariance and Symmetry Breaking in Convolutional Networks (NeurIPS 2025 · similarity 0.88)
- A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs (ICML 2024 · similarity 0.87)
- On Making $SE(2)$-Invariant Networks Optimal (NeurIPS 2026 · 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.