Research map / Architectures and efficiency / Spiking networks
Temporal-Wise Attention Spiking Neural Networks for Event Streams Classification
Man Yao, Huanhuan Gao, Guangshe Zhao, Dingheng Wang, Yihan Lin, Zhaoxu Yang, 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 temporal-wise attention (TA) (ablation) | LIF SNN · DVS128 Gesture (S3, T=60, dt=1ms) | accuracy: 71.53 -> 73.25 | Improved |
| add temporal-wise attention (TA) (ablation) | LIAF SNN · DVS128 Gesture (S3, T=60, dt=25ms) | accuracy: 96.18 -> 98.61 | Improved |
| add TA (ablation) | LIF SNN · CIFAR10-DVS | accuracy: 66.60 -> 71.10 | Improved |
| add TA (ablation) | LIAF SNN · CIFAR10-DVS | accuracy: 70.97 -> 72.00 | Improved |
| add TA (ablation) | LIF SNN · SHD (dt=4ms, T=150) | accuracy: 74.16 -> 85.91 | Improved |
| add random consecutive slice (RCS) augmentation (ablation) | LIF SNN · DVS128 Gesture (S3, T=60, dt=1ms) | accuracy: 71.53 -> 87.15 | Improved |
| add RCS augmentation (ablation) | LIAF TA-SNN · DVS128 Gesture (S3, T=60, dt=25ms) | accuracy: 98.61 -> 94.79 | Hurt |
| add RCS augmentation (ablation) | LIF TA-SNN · DVS128 Gesture (S3, T=60, dt=1ms) | accuracy: 73.25 -> 90.28 | Improved |
| add RCS augmentation (ablation) | LIAF SNN · CIFAR10-DVS | accuracy: 69.40 -> 70.97 | Improved |
| insert TA at the whole network (S4) in addition to the depth layers (ablation) | TA-SNN · DVS128 Gesture (position study) | accuracy | Hurt |
| insert TA only at depth layers (S3) instead of input layer only (S2) (ablation) | TA-SNN · DVS128 Gesture (position study) | accuracy | Improved |
| input attention pruning at 0.5 proportion vs random pruning (ablation) | TA-SNN · DVS128 Gesture (IAP) | accuracy: 78% -> 89% | Improved |
Closest papers by meaning
- STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks (CVPR 2025 · similarity 0.88)
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.87)
- Advancing Spiking Neural Networks Towards Multiscale Spatiotemporal Interaction Learning (AAAI 2025 · similarity 0.87)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.87)
- An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain (AAAI 2024 · similarity 0.86)
- Spiking Neural Network as Adaptive Event Stream Slicer (NeurIPS 2024 · similarity 0.86)
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.
