Research map / Architectures and efficiency / Spiking networks
Reducing Information Loss for Spiking Neural Networks
Yufei Guo, Yuanpei Chen, Liwen Zhang, YingLei Wang, Xiaode Liu, Xinyi Tong, Yuanyuan Ou, 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 |
|---|---|---|---|
| replace hard-reset LIF with soft-reset IF (SRIF) (ablation) | IF/LIF neuron, ResNet20 · CIFAR-10 (T=4) | accuracy: 92.22% -> 92.46% | Improved |
| replace hard-reset IF with soft-reset IF (SRIF) (ablation) | ResNet20 · CIFAR-100 (T=4) | accuracy: 66.95% -> 67.90% | Improved |
| replace hard-reset IF with SRIF at 8 timesteps (ablation) | ResNet20 · CIFAR-10 (T=8) | accuracy: 92.86% -> 94.09% | Improved |
| replace hard-reset IF with SRIF at 2 timesteps (ablation) | ResNet20 · CIFAR-10 (T=2) | accuracy: 90.07% -> 90.38% | Improved |
| replace hard-reset LIF with SRIF at 8 timesteps (ablation) | ResNet20 · CIFAR-100 (T=8) | accuracy: 67.85% -> 69.90% | Improved |
| use LIF instead of IF neuron (hard reset) (ablation) | ResNet20 · CIFAR-100 (T=4) | accuracy: 66.95% -> 66.00% | Hurt |
| use LIF instead of IF neuron (hard reset) (ablation) | ResNet20 · CIFAR-10 (T=4) | accuracy: 92.04% -> 92.22% | Improved |
| add MPR to SRIF (ablation) | ResNet20 · CIFAR-100 (T=4) | accuracy: 67.90% -> 70.63% | Improved |
| add MPR to SRIF (ablation) | ResNet20 · CIFAR-10 (T=4) | accuracy: 92.46% -> 92.94% | Improved |
| add MPR to SRIF (ablation) | ResNet19 · CIFAR-10 (T=4) | accuracy: 95.44% -> 96.27% | Improved |
| add MPR to SRIF (ablation) | ResNet19 · CIFAR-100 (T=4) | accuracy: 77.85% -> 78.42% | Improved |
| apply MPR to membrane potential (ablation) | ResNet20 · CIFAR-10 (T=4) | avg quantization error: 0.28 -> 0.04 | Improved |
Closest papers by meaning
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.90)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.88)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.88)
- S$^2$NN: Sub-bit Spiking Neural Networks (NeurIPS 2025 · similarity 0.87)
- Robust Stable Spiking Neural Networks (ICML 2024 · similarity 0.87)
- Rethinking Spiking Neural Networks from an Ensemble Learning Perspective (ICLR 2025 · similarity 0.87)
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.
