Research map / Architectures and efficiency / Spiking networks
Near Lossless Transfer Learning for 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 |
|---|---|---|---|
| Train with clamping and quantization before transferring CNN weights to the SNN | CNN-to-SNN transfer on MNIST · MNIST | conversion accuracy loss: 1.77% -> 0.05% | Helped |
| Train with clamping and quantization before transferring CNN weights to the SNN | CNN-to-SNN transfer on MNIST · MNIST | conversion accuracy loss: 88.65% -> 0.01% | Helped |
| Use deterministic evenly distributed input spikes instead of randomly sampled spikes (ablation) | SNN input encoding · SNN experiments | accuracy: +8.33% | Helped |
| Quantize VGG-19 SNN weights from 32 bits to 11 bits (ablation) | VGG-19 SNN · CIFAR-10 | accuracy: 93.44 -> 93.44 | No clear effect |
| Quantize VGG-19 SNN weights from 32 bits to 10 bits (ablation) | VGG-19 SNN · CIFAR-10 | accuracy: 93.44 -> 93.42 | No clear effect |
| Quantize VGG-19 SNN weights from 32 bits to 9 bits (ablation) | VGG-19 SNN · CIFAR-10 | accuracy: 93.44 -> 93.43 | No clear effect |
| Quantize VGG-19 SNN weights from 32 bits to 8 bits (ablation) | VGG-19 SNN · CIFAR-10 | accuracy: 93.44 -> 92.82 | Hurt |
| Use weights of 7 bits or fewer (ablation) | VGG-19 SNN · CIFAR-10 | accuracy | Hurt |
Closest papers by meaning
- QP-SNN: Quantized and Pruned Spiking Neural Networks (ICLR 2025 · similarity 0.89)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.89)
- Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications (CVPR 2025 · similarity 0.88)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.88)
- Enhancing Training of Spiking Neural Network with Stochastic Latency (AAAI 2024 · similarity 0.88)
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 2025 · 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.