AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Masked Spiking Transformer

Ziqing Wang, Yuetong Fang, Jiahang Cao, Qiang Zhang, Zhongrui Wang, Renjing Xu

ICCV 2023 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 62 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 Random Spike Masking at 75% ratio to the self-attention module (ablation)MST · CIFAR-10accuracy and power: 97.27 -> 97.29 accuracy; power x0.74Improved
apply Random Spike Masking at 50% ratio (ablation)Spiking ResNet18 · CIFAR-10accuracy: 96.48 -> 92.88Hurt
apply Random Spike Masking at 75% ratio (ablation)Spiking VGG16 · CIFAR-10accuracy: 95.46 -> 79.09Hurt
mask the MLP module instead of the self-attention module (ablation)MST · CIFAR-10/CIFAR-100accuracy vs masking ratioHurt
increase number of masked blocks beyond 2-5 (ablation)MST · CIFAR-100accuracyHurt
use BatchNorm instead of LayerNorm in ANN-to-SNN conversion (ablation)MST · Membrane potential distributionANN-SNN distribution matchImproved
increase time steps from 64 to 256 (ablation)MST · CIFAR-100top-1 accuracy (%): 85.40 -> 86.91Improved
fine-tune masked student with unmasked teacher (distillation)MST with RSM · CIFARaccuracyImproved

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