AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model

Zecheng Hao, Yifan Huang, Zijie Xu, Wenxuan Liu, Yuanhong Tang, Zhaofei Yu, Tiejun Huang

CVPR 2026 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 2 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 LIF with HD-LIF in online training (ablation)online SNN training, ResNet-18 · CIFAR-100 ablation configaccuracy (%): 71.75 -> 80.16Improved
compress firing spikes to 4 bits (ablation)HD-LIF · CIFAR-100 ablation configenergy (mJ): 0.26 -> 0.03 (accuracy 80.16 -> 79.62)Improved
use Parallel HD-LIF in 50% of layers (ablation)HD-LIF · CIFAR-100 ablation configNOPs (M): 6.59 -> 4.62Improved
use Parallel HD-LIF in 50% of layers (ablation)HD-LIF · CIFAR-100 ablation configaccuracy (%): 80.16 -> 78.82Hurt
add Mem-BN and SECA attention (ablation)HD-LIF ResNet-18 · CIFAR-10accuracy (%): 95.59 -> 95.91Improved
add Mem-BN and SECA attention (ablation)HD-LIF ResNet-18 · CIFAR-100accuracy (%): 78.45 -> 79.33Improved
add Mem-BN and SECA attention (ablation)HD-LIF ResNet-18 · DVS-CIFAR10accuracy (%): 81.70 -> 83.50Improved
use HD-LIF with 4-bit spikes and weight compression instead of online SLTTResNet-18 online training · CIFAR-100accuracy (%): 74.38 -> 78.45Improved
use HD-LIF instead of OTTT/SLTT online trainingResNet-34 · ImageNet-1kaccuracy (%): 66.19 -> 69.77Improved

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