Research map / Architectures and efficiency / Spiking networks
Temporal Effective Batch Normalization in 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 |
|---|---|---|---|
| replace tdBN with TEBN (time-step-specific learnable scaling) | ResNet-19, T=2 · CIFAR-10 | accuracy (%): 92.34 -> 94.57 | Helped |
| replace BNTT with TEBN | VGG-11 SNN · CIFAR-100 | accuracy (%): 66.60 -> 74.37 | Helped |
| replace NeuNorm with TEBN | 7-layer CNN SNN · DVS-CIFAR10 | accuracy (%): 60.50 -> 75.10 | Helped |
| replace tdBN with TEBN | ResNet-34 SNN · ImageNet | accuracy (%): 63.72 -> 64.29 | Helped |
| replace TET with TEBN | SEW ResNet-34 · ImageNet | accuracy (%): 68.00 -> 68.28 | Helped |
| add cutout augmentation | TEBN ResNet-19, T=6 · CIFAR-100 | accuracy (%): 76.41 -> 78.76 | Helped |
| use TEBN instead of other BN methods across initial membrane time constant tau | 9-layer CNN, T=2 · CIFAR-10 | accuracy (%) | Helped |
Closest papers by meaning
- TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks (ICLR 2024 · similarity 0.93)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.90)
- Training High Performance Spiking Neural Network by Temporal Model Calibration (ICML 2025 · similarity 0.90)
- Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons (ICML 2025 · similarity 0.88)
- Enhancing Training of Spiking Neural Network with Stochastic Latency (AAAI 2024 · similarity 0.88)
- TS-SNN: Temporal Shift Module for Spiking Neural Networks (ICML 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.