Research map / Architectures and efficiency / CNN design
Reversible Architectures for Arbitrarily Deep Residual Neural Networks
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 Hamiltonian instead of ResNet | classification network · CIFAR-10, training with 3% and 4% of training data | accuracy: up to 13% higher accuracy | Helped |
| Use Hamiltonian instead of ResNet | classification network · STL-10, reduced training data | accuracy: around 3.4% | Helped |
| Use Hamiltonian instead of ResNet | classification network · STL-10, using 40% of training data | accuracy: 5.7% higher accuracy | Helped |
| Use a 1202-layer Hamiltonian architecture instead of ResNet-1202 | CIFAR-10 classifier · CIFAR-10 | accuracy: 92.07% -> 93.84% | Helped |
| Use Hamiltonian, MidPoint, or Leapfrog instead of the cited benchmark methods | STL-10 classifier · STL-10 | accuracy: All our three architectures outperform the benchmark methods by about 10%. | Helped |
Closest papers by meaning
- The Reversible Residual Network: Backpropagation Without Storing Activations (NeurIPS 2017 · similarity 0.90)
- Simplified Reversible Residual Networks (NeurIPS 2026 · similarity 0.90)
- Implicit regularization of deep residual networks towards neural ODEs (ICLR 2024 · similarity 0.87)
- Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning (CVPR 2024 · similarity 0.87)
- Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers (NeurIPS 2025 · similarity 0.86)
- Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization (NeurIPS 2024 · 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.