Research map / Architectures and efficiency / Spiking networks
Reducing ANN-SNN Conversion Error through Residual Membrane Potential
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 SRP to QCFS conversion | VGG-16 · CIFAR-10, T=4 | top-1 accuracy: 83.75% -> 90.51% | Helped |
| Add SRP to QCFS conversion | VGG-16 · CIFAR-10, T=4 | top-1 accuracy: 93.96% -> 95.32% | Helped |
| Add SRP to QCFS conversion | VGG-16 · CIFAR-100, T=4 | top-1 accuracy: 69.62% -> 75.42% | Helped |
| Add SRP to QCFS conversion | ResNet-20 · CIFAR-100, T=4 | top-1 accuracy: 34.14% -> 59.34% | Helped |
| Add SRP to QCFS conversion | VGG-16 · ImageNet, T=2 | top-1 accuracy: 50.97% -> 61.37% | Helped |
| Add SRP to QCFS conversion | ResNet-34 · ImageNet, T=8 | top-1 accuracy: 59.35% -> 67.62% | Helped |
| Increase τ from 2 to 4 (ablation) | SRP on VGG-16 · CIFAR-100, T=4 | top-1 accuracy: 73.21% -> 75.42% | Helped |
| Increase τ from 4 to 8 (ablation) | SRP on VGG-16 · CIFAR-100, T=4 | top-1 accuracy: 75.42% -> 76.25% | Helped |
| Increase τ from 8 to 16 (ablation) | SRP on VGG-16 · CIFAR-100, T=4 | top-1 accuracy: 76.25% -> 76.55% | Helped |
| Increase τ from 2 to 4 (ablation) | SRP on ResNet-20 · CIFAR-100, T=4 | top-1 accuracy: 47.72% -> 59.34% | Helped |
| Increase τ from 4 to 8 (ablation) | SRP on ResNet-20 · CIFAR-100, T=4 | top-1 accuracy: 59.34% -> 66.44% | Helped |
| Increase τ from 8 to 16 (ablation) | SRP on ResNet-20 · CIFAR-100, T=4 | top-1 accuracy: 66.44% -> 68.07% | Helped |
Closest papers by meaning
- Efficient ANN-SNN Conversion with Error Compensation Learning (ICML 2025 · similarity 0.92)
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.91)
- Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation (ICML 2025 · similarity 0.91)
- Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications (CVPR 2025 · similarity 0.91)
- Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons (ICML 2025 · similarity 0.90)
- Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks (AAAI 2025 · similarity 0.90)
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.