Research map / Architectures and efficiency / CNN design
SplineNets: Continuous Neural Decision Graphs
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 |
|---|---|---|---|
| Increase the number of knots from two to five (ablation) | Spline-ResNet-32 with convolutional decisions and rank-3 knots · CIFAR-10 | accuracy | Helped |
| Increase the number of knots from two to five (ablation) | Spline-ResNet-32 with convolutional decisions and rank-3 knots · CIFAR-10 | single-sample inference FLOPS | No clear effect |
| Use hierarchical rather than dynamic-only conditioning (ablation) | Spline-ResNet-32 · CIFAR-10 | accuracy | No clear effect |
| Set the ResNet diffusion rate to 0.875 (ablation) | Spline-ResNet · CIFAR-10 | accuracy | No clear effect |
| Use mutual-information regularization (ablation) | Spline-LeNet · CIFAR-10 | accuracy | Helped |
| Use mutual-information regularization (ablation) | Spline-ResNet · CIFAR-10 | accuracy | No clear effect |
| Use rank-3 rather than rank-4 knots (ablation) | Spline-ResNet · CIFAR-10 | model size | Mixed |
| Replace LeNet-32 with H(2)-D-R3 | LeNet-32 · MNIST original | accuracy: 99.52% -> 99.61% | Helped |
| Replace LeNet-32 with H(2)-D-R3 | LeNet-32 · MNIST augmented | accuracy: 99.60% -> 99.65% | Helped |
Closest papers by meaning
- No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths (ICML 2024 · similarity 0.86)
- On the Hardness of Training Deep Neural Networks Discretely (AAAI 2025 · similarity 0.85)
- PICNN: A Pathway towards Interpretable Convolutional Neural Networks (AAAI 2024 · similarity 0.85)
- LINE: LLM-based Iterative Neuron Explanations for Vision Models (NeurIPS 2026 · similarity 0.85)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.85)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · 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.