Research map / Architectures and efficiency / Spiking networks
Real Spike: Learning Real-Valued Spikes for Spiking Neural Networks
Yufei Guo, Liwen Zhang, Yuanpei Chen, Xinyi Tong, Xiaode Liu, YingLei Wang, Xuhui Huang, Zhe Ma
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 |
|---|---|---|---|
| use real-valued spikes instead of binary spikes (T=2) (ablation) | ResNet20 SNN · CIFAR-10 (T=2) | accuracy (%): 88.91 -> 90.47 | Improved |
| use real-valued spikes instead of binary spikes (T=4) (ablation) | ResNet20 SNN · CIFAR-10 (T=4) | accuracy (%): 91.73 -> 92.53 | Improved |
| use real-valued spikes instead of binary spikes (T=6) (ablation) | ResNet20 SNN · CIFAR-10 (T=6) | accuracy (%): 92.98 -> 93.44 | Improved |
| use real-valued spikes instead of binary spikes (T=2) (ablation) | ResNet20 SNN · CIFAR-100 (T=2) | accuracy (%): 62.59 -> 63.40 | Improved |
| use real-valued spikes instead of binary spikes (T=4) (ablation) | ResNet20 SNN · CIFAR-100 (T=4) | accuracy (%): 63.27 -> 64.87 | Improved |
| use real-valued spikes instead of binary spikes (T=6) (ablation) | ResNet20 SNN · CIFAR-100 (T=6) | accuracy (%): 67.12 -> 68.60 | Improved |
| layer-wise real spike coefficient (ablation) | ResNet20 SNN · CIFAR-10 (T=4) | accuracy (%): 91.73 -> 92.12 | Improved |
| channel-wise instead of layer-wise coefficient (ablation) | ResNet20 SNN · CIFAR-10 (T=4) | accuracy (%): 92.12 -> 92.25 | Improved |
| element-wise instead of channel-wise coefficient (ablation) | ResNet20 SNN · CIFAR-10 (T=4) | accuracy (%): 92.25 -> 92.53 | Improved |
| element-wise instead of layer-wise coefficient (ablation) | ResNet20 SNN · CIFAR-100 (T=4) | accuracy (%): 64.28 -> 64.87 | Improved |
| Real Spike vs STBP-tdBN with fewer timesteps (2 vs 6) | ResNet19 SNN · CIFAR-10 | accuracy (%): 93.16 -> 94.01 | Improved |
| Real Spike vs SEW ResNet on ImageNet | ResNet34 SNN · ImageNet | accuracy (%): 67.04 -> 67.69 | Improved |
Later papers that compared with this method
6 later accepted papers report Real Spike as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- Advancing Spatiotemporal Representations in Spiking Neural Networks via Parametric Invertible Transformation (ICLR 2026 · better on 1 of 1 shared result)
- FSTA-SNN:Frequency-Based Spatial-Temporal Attention Module for Spiking Neural Networks (AAAI 2025 · better on 2 of 2 shared results)
- STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks (CVPR 2025 · better on 1 of 1 shared result)
- TS-SNN: Temporal Shift Module for Spiking Neural Networks (ICML 2025 · better on 1 of 1 shared result)
- Enhancing Representation of Spiking Neural Networks via Similarity-Sensitive Contrastive Learning (AAAI 2024 · better on 2 of 3 shared results)
- Membrane Potential Batch Normalization for Spiking Neural Networks (ICCV 2023 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Direct Training for Spiking Neural Networks: Faster, Larger, Better (AAAI 2019 · similarity 0.91)
- Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation (ICLR 2020 · similarity 0.91)
- Scaling Spike-Driven Transformer With Efficient Spike Firing Approximation Training (TPAMI 2025 · similarity 0.90)
- QP-SNN: Quantized and Pruned Spiking Neural Networks (ICLR 2025 · similarity 0.90)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.90)
- Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers (NeurIPS 2025 · similarity 0.89)
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.
