AI Paper Atlas

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

TPAMI 2023 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 304 citations (OpenAlex)

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 changedWhereMeasuredEffect
add TCSA attention to vanilla SNN3-layer SNN · DVS128 Gestureaccuracy (%): 90.63 -> 96.53 (+5.9)Improved
add TCSA attention to vanilla SNN5-layer SNN · DVS128 Gestureaccuracy (%): 95.58 -> 98.23 (+2.7)Improved
add TCSA attention to vanilla SNN3-layer SNN · DVS128 Gaitaccuracy (%): 87.59 -> 92.29 (+4.7)Improved
add TCSA attention to vanilla SNN3-layer SNN · DVS128 Gesturespike counts: 0.173 -> 0.026 NASAR (-84.9%)Improved
add CSA attention to MS-Res-SNN-34MS-Res-SNN-34 · ImageNet-1K (T=1)top-1 accuracy (%): 64.13 -> 69.15 (+5.0)Improved
add CSA attention to MS-Res-SNN-104MS-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 -> 73.82Improved
place channel attention at Activate-PRE rather than Conv-PRE (ablation)CA-SNN · DVS128 Gestureaccuracy (%): 91.84 -> 93.88Improved
add temporal attention to CA (TCA vs CA) (ablation)SNN · DVS128 Gestureaccuracy (%): 93.88 -> 95.73Improved
add all three dimensions TCSA vs TCA (ablation)SNN · DVS128 Gestureaccuracy (%): 95.73 -> 96.53Improved
use ECA instead of CBAM (ablation)3-layer SNN · DVS128 Gestureaccuracy (%): 93.88 -> 92.81Hurt
use SimAM instead of CBAM (ablation)3-layer SNN · DVS128 Gestureaccuracy (%): 93.88 -> 91.98Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy