AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization

Ruichen Ma, Xiaoyang Zhang, Jian Bai, Guanchao Qiao, Liwei Meng, Ning Ning, Yang Liu, Shaogang Hu

ECCV 2026 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 0 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 IS-SNN (topology-aware WS, no BN) instead of no normalizationResNet-34 · ImageNet (T=4)accuracy (%): 32.58 -> 66.61Improved
extend ImageNet training from 128 to 400 epochsIS-SNN ResNet-34 · ImageNetaccuracy (%): 66.61 -> 68.05Improved
add IS-SNN to a BN-free SEW-ResNet-152ResNet-152 · CIFAR-100 (T=4)accuracy (%): 17.10 -> 76.98Improved
add IS-SNN to a BN-free VGG-9VGG-9 · CIFAR-10 (T=4)accuracy (%): 10.00 -> 92.91Improved
add IS-SNN to a BN-free 7B-Net7B-Net · DVS-Gesture (T=16)accuracy (%): 77.08 -> 96.88Improved
add IS-SNN to a BN-free VGGSNNVGGSNN · CIFAR10-DVS (T=8)accuracy (%): 10.0 -> 77.7Improved
add IS-SNN to ResNet-19 without BN with absolute gainsResNet-19 · CIFAR-10 and CIFAR-100accuracy (%): +4.49% on CIFAR-10 and +8.58% on CIFAR-100Improved
use topology-aware gamma instead of gamma fixed to 1 (naive WS) (ablation)IS-SNN VGG-11 · CIFAR-10accuracy (%): 10.00 -> 95.06Improved
use topology-aware gamma instead of gamma fixed to 1 (naive WS) (ablation)IS-SNN ResNet-19 · CIFAR-100accuracy (%): 70.69 -> 76.02Improved
use topology-aware gamma instead of gamma fixed to 1 (naive WS) (ablation)IS-SNN ResNet-19 · CIFAR-10accuracy (%): 92.05 -> 94.32Improved
add IS-SNN to ResNet-19B with five transition blocks (ablation)ResNet-19B · CIFAR-100accuracy (%): 1.00 -> 78.71Improved
set residual scale alpha=0.5 versus alpha=1.0 (ablation)IS-SNN ResNet · CIFAR-10/100accuracy (%): gap between alpha=0.5 and alpha=1.0 below 0.2%No clear effect

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