AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow

Jingtao Wang, Zengjie Song, Yuxi Wang, Jun Xiao, Yuran Yang, Shuqi Mei, Zhaoxiang Zhang

ICCV 2023 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 5 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 backprop through membrane accumulation with stabilized spiking flow mappingTET, RecDis, SEW, tdBN · CIFAR-10/CIFAR-100/TinyImageNet (T=20)backward time speed-up: 2.01x to 2.95x speed-up with accuracy on parImproved
apply SSF to TET on neuromorphic dataTET · DVS-CIFAR10 (T=20)accuracy: 78.7% -> 74.1%Hurt
swap TET loss for cross-entropy loss when using SSF (ablation)TET + SSF · DVS-CIFAR10 (T=20)accuracy: 74.1% -> 78.0%Improved
use learned average spiking electricity R instead of fixed R=1 (ablation)SSF · CIFAR-10accuracy: 10.00% -> 95.19%Improved
use fine-grained R (per element) instead of coarser R (per batch or per batch and channel) (ablation)SSF · CIFAR-10accuracy: 60.19% -> 95.19%Improved
use a single scalar R instead of per-element R (ablation)SSF · CIFAR-10accuracy: 95.19% -> 94.41%Hurt
SSF instead of DSR without firing mechanism modification, fewer time stepsIF SNN · CIFAR-10 (T=5)accuracy: 84.0% -> 95.0%Improved
increase number of GPUs from 1 to 8 (ablation)SSF speed-up · TET on CIFAR-10speed-up ratio: 3.04 -> 2.96No clear effect
increase time steps up to 80 with SSFSSF · TET training timespeed-up ratio: about 10x at T=80Improved

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