Research map / Architectures and efficiency / Spiking networks
Attention Spiking Neural Networks
Man Yao, Guangshe Zhao, Hengyu Zhang, Yifan Hu, Lei Deng, Yonghong Tian, Bo Xu, Guoqi Li
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 |
|---|---|---|---|
| add TCSA attention to vanilla SNN | 3-layer SNN · DVS128 Gesture | accuracy (%): 90.63 -> 96.53 (+5.9) | Improved |
| add TCSA attention to vanilla SNN | 5-layer SNN · DVS128 Gesture | accuracy (%): 95.58 -> 98.23 (+2.7) | Improved |
| add TCSA attention to vanilla SNN | 3-layer SNN · DVS128 Gait | accuracy (%): 87.59 -> 92.29 (+4.7) | Improved |
| add TCSA attention to vanilla SNN | 3-layer SNN · DVS128 Gesture | spike counts: 0.173 -> 0.026 NASAR (-84.9%) | Improved |
| add CSA attention to MS-Res-SNN-34 | MS-Res-SNN-34 · ImageNet-1K (T=1) | top-1 accuracy (%): 64.13 -> 69.15 (+5.0) | Improved |
| add CSA attention to MS-Res-SNN-104 | MS-Res-SNN-104 · ImageNet-1K (T=1) | top-1 accuracy (%): 71.57 -> 73.82 (+2.3) | Improved |
| add spatial attention to CA (CSA vs CA) (ablation) | MS-Res-SNN-104 · ImageNet-1K (T=1) | top-1 accuracy (%): 72.03 -> 73.82 | Improved |
| place channel attention at Activate-PRE rather than Conv-PRE (ablation) | CA-SNN · DVS128 Gesture | accuracy (%): 91.84 -> 93.88 | Improved |
| add temporal attention to CA (TCA vs CA) (ablation) | SNN · DVS128 Gesture | accuracy (%): 93.88 -> 95.73 | Improved |
| add all three dimensions TCSA vs TCA (ablation) | SNN · DVS128 Gesture | accuracy (%): 95.73 -> 96.53 | Improved |
| use ECA instead of CBAM (ablation) | 3-layer SNN · DVS128 Gesture | accuracy (%): 93.88 -> 92.81 | Hurt |
| use SimAM instead of CBAM (ablation) | 3-layer SNN · DVS128 Gesture | accuracy (%): 93.88 -> 91.98 | Hurt |
Closest papers by meaning
- STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks (CVPR 2025 · similarity 0.92)
- FSTA-SNN:Frequency-Based Spatial-Temporal Attention Module for Spiking Neural Networks (AAAI 2025 · similarity 0.91)
- Advancing Spiking Neural Networks Towards Multiscale Spatiotemporal Interaction Learning (AAAI 2025 · similarity 0.91)
- Gated Attention Coding for Training High-Performance and Efficient Spiking Neural Networks (AAAI 2024 · similarity 0.90)
- Brain-Inspired Spiking Neural Networks for Energy-Efficient Object Detection (CVPR 2025 · similarity 0.90)
- Spiking Vision Transformer with Saccadic Attention (ICLR 2025 · similarity 0.90)
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.
