AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Spiking Wavelet Transformer

Yuetong Fang, Ziqing Wang, Lingfeng Zhang, Jiahang Cao, Honglei Chen, Renjing Xu

ECCV 2024 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 26 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
Replace spiking self-attention with the Frequency-Aware Token MixerSpiking Transformer · ImageNettop-1 accuracy (%): 72.46 -> 74.98Improved
Add spiking wavelet transform branch (ablation)SWformer · CIFAR-100accuracy (%): 78.89 -> 79.31Improved
Add spiking wavelet transform branch (ablation)SWformer · CIFAR10-DVSaccuracy (%): 80.9 -> 83.9Improved
Add negative spike dynamics (ternary spikes) in the wavelet transform (ablation)SWformer · CIFAR-100accuracy (%): 78.64 -> 79.31Improved
Add spiking Haar inverse transform (ablation)SWformer · CIFAR-100accuracy (%): 78.79 -> 79.31Improved
Add 1D max-pooling at the start of FATM (ablation)SWformer · CIFAR10-DVSaccuracy (%): 81.8 -> 83.9Improved
Mask DC (low-frequency) components (ablation)SWformer · CIFAR-100 / CIFAR10-DVSaccuracy (%): 79.31 -> 79.34; 83.9 -> 84.0No clear effect
Increase weight splitting blocks from 2 to 4 (ablation)SWformer · ImageNetparameters and accuracy: 21.8M -> 18.46M params, 74.98 -> 74.62 (Vth=0.5)Improved
Use standard non-spiking wavelet instead of spiking Haar (ablation)SWformer* · ImageNettop-1 accuracy (%): 75.18 -> 75.26 (B=2, Transformer-8-512)Improved
Increase firing threshold of spiking frequency representation (ablation)SWformer (Block=4) · ImageNetpower: 58.4% to 60.1% reductionImproved
Use SWformer on neuromorphic dataN-Caltech101, N-Cars · neuromorphic datasetsaccuracy (%): NDA 83.70 -> 88.45; 91.90 -> 96.32Improved

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