Research map / Architectures and efficiency / Spiking networks
Activation-wise Propagation: A One-Timestep Strategy for Spiking Neural Networks
Jian Song, Xiangfei Yang, Shangke Lyu, Donglin Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 AMP2 at T=1 | SEWResNet · DVS128Gesture frame (T=4) | accuracy: 88.19 -> 93.75 (+5.56) | Improved |
| add AMP2 | Spiking ResNet · DVS128Gesture frame (T=4) | accuracy: 71.88 -> 82.29 (+10.41) | Improved |
| add AMP2 | Spiking PlainNet · DVS128Gesture frame (T=4) | accuracy: 75.0 -> 78.13 (+3.13) | Improved |
| add AMP2 at T=1 | Spiking PointNet · DVS128Gesture point | accuracy: 31.22 -> 92.82 | Improved |
| add AMP2 at T=1 | Spiking PointNet · ModelNet40 OA | overall accuracy: 87.36 -> 89.74 | Improved |
| add AMP2 at T=1 | Spiking PointNet++ SSG · ScanObjectNN OA | overall accuracy: 48.01 -> 72.57 | Improved |
| add AMP2 at T=1 vs 4-timestep SNN | Spiking PointNet · ShapeNetPart instance mIoU | mIoU: 81.38 -> 82.44 | Improved |
| add AMP2 at T=1 vs 4-timestep SNN | Spiking PointNet++ · DVS128Gesture point | accuracy: 94.68 -> 92.89 | Hurt |
| add AWP (ablation) | Spiking PointNet++ SSG with 3 SA · ModelNet40 | overall accuracy: 87.35 -> 88.55 | Improved |
| add RMP (ablation) | Spiking PointNet++ SSG with 3 SA · ModelNet40 | overall accuracy: 87.35 -> 89.88 | Improved |
| add both AWP and RMP (ablation) | Spiking PointNet++ SSG with 3 SA · ModelNet40 | overall accuracy: 87.35 -> 91.23 | Improved |
| add RMP (ablation) | Spiking PointNet++ SSG with 6 SA · ModelNet40 | overall accuracy: 78.71 -> 89.29 | Improved |
Closest papers by meaning
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.92)
- Rethinking Spiking Neural Networks from an Ensemble Learning Perspective (ICLR 2025 · similarity 0.89)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.89)
- Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment (ICML 2025 · similarity 0.89)
- Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation (ICML 2025 · similarity 0.88)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.88)
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.
