Research map / Architectures and efficiency / Spiking networks
Constructing Deep Spiking Neural Networks From Artificial Neural Networks With Knowledge Distillation
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 |
|---|---|---|---|
| Distill the ANN teacher's output responses into the SNN | CIFAR10 SNN · CIFAR10 | accuracy (%): 88.44 -> 89.12 | Helped |
| Distill the ANN teacher's intermediate features into the SNN | WRN16-2 SNN · CIFAR10 | accuracy (%): 90.34 -> 92.10 | Helped |
| Use feature-based rather than response-based distillation | WRN16-2 SNN with Pyramidnet18 teacher · CIFAR10 | accuracy (%): 91.11 -> 92.10 | Helped |
| Use feature-based rather than response-based distillation | WRN16-2 SNN with WRN28-4 teacher · CIFAR10 | accuracy (%): 91.14 -> 91.03 | No clear effect |
| Distill ANN knowledge into the SNN | VGG11 SNN · CIFAR10, Gaussian noise (σ = 0.01) | accuracy (%): 81.63 -> 82.90 | Helped |
| Distill ANN knowledge into the SNN | VGG11 SNN · CIFAR10, Gaussian noise (σ = 0.03) | accuracy (%): 76.42 -> 77.96 | Helped |
| Distill ANN knowledge into the SNN | VGG11 SNN · CIFAR10, Gaussian noise (σ = 0.05) | accuracy (%): 73.40 -> 74.23 | Helped |
| Distill ANN knowledge into the SNN | 2conv SNN · MNIST, Background | accuracy (%): 95.04 -> 96.35 | Helped |
| Distill ANN knowledge into the SNN | 2conv SNN · MNIST, Random noise | accuracy (%): 95.31 -> 95.79 | Helped |
| Distill ANN knowledge into the SNN | 2conv SNN · MNIST, Rotation | accuracy (%): 94.43 -> 95.34 | Helped |
| Distill ANN knowledge into the SNN | 2conv SNN · MNIST, Rotation with background | accuracy (%): 80.96 -> 81.82 | Helped |
| Use a four-timestep KDSNN instead of the reported ASF-BP model | MNIST SNN · MNIST | timestep: 400 -> 4 | Helped |
Closest papers by meaning
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 2025 · similarity 0.93)
- Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement (CVPR 2025 · similarity 0.92)
- Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers (NeurIPS 2025 · similarity 0.92)
- Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks (CVPR 2025 · similarity 0.92)
- Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment (ICML 2025 · similarity 0.91)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · 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.