Research map / Architectures and efficiency / Spiking networks
SpikeConverter: An Efficient Conversion Framework Zipping the Gap between Artificial Neural Networks and Spiking 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 SpikeConverter instead of TSC conversion | ResNet-20 · CIFAR-10 | Top-1 accuracy: 91.42% -> 91.47% | Helped |
| Use SpikeConverter instead of TSC conversion | VGG-16 · CIFAR-10 | Top-1 accuracy: 93.63% -> 93.71% | Helped |
| Use SpikeConverter instead of TSC conversion | ResNet-20 · CIFAR-100 | Top-1 accuracy: 68.18% -> 68.69% | Helped |
| Use SpikeConverter instead of TSC conversion | VGG-16 · CIFAR-100 | Top-1 accuracy: 70.97% -> 71.22% | Helped |
| Use SpikeConverter instead of TSC conversion | ResNet-34 · ImageNet validation | Top-1 accuracy: 69.93% -> 70.57% | Helped |
| Use SpikeConverter instead of TSC conversion | VGG-16 · ImageNet validation | Top-1 accuracy: 73.46% -> 73.47% | No clear effect |
| Use SpikeConverter instead of TSC conversion | ResNet-34 · ImageNet validation | time steps: 4096 -> 16 | Helped |
| Use SpikeConverter instead of TSC conversion | VGG-16 · CIFAR-10 | time steps: 2048 -> 16 | Helped |
| Set the iLIF damping coefficient to k=2 (ablation) | SpikeConverter · conversion parameter analysis | conversion error | Helped |
| Increase output spike-train length from 4 to 16 time steps (ablation) | SpikeConverter VGG-16 · CIFAR-10 | Top-1 accuracy: ≤0.6% accuracy change | Mixed |
Closest papers by meaning
- Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications (CVPR 2025 · similarity 0.93)
- Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation (ICML 2025 · similarity 0.93)
- Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks (AAAI 2025 · similarity 0.91)
- Efficient ANN-SNN Conversion with Error Compensation Learning (ICML 2025 · similarity 0.91)
- SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation (NeurIPS 2024 · similarity 0.91)
- Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons (ICML 2025 · similarity 0.91)
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.