AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

DS-ATGO: Dual-Stage Synergistic Learning via Forward Adaptive Threshold and Backward Gradient Optimization for Spiking Neural Networks

Jiaqiang Jiang, Wenfeng Xu, Jing Fan, Rui Yan

AAAI 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
add adaptive threshold (AT) (ablation)Vanilla-SNN · CIFAR10 / CIFAR10-DVSaccuracyImproved
add threshold-driven gradient optimization (TGO) (ablation)Vanilla-SNN · CIFAR10 / CIFAR10-DVSaccuracyImproved
combine AT and TGO (ablation)Vanilla-SNN · CIFAR10accuracy (%): +1.71%Improved
combine AT and TGO (ablation)Vanilla-SNN · CIFAR10-DVSaccuracy (%): +2.30%Improved
use true MPD distribution instead of estimated normal distribution (ablation)DS-ATGO · CIFAR100 / CIFAR10-DVSaccuracyImproved
add moving average of thresholds for inference (ablation)DS-ATGO · CIFAR100 / CIFAR10-DVSaccuracyImproved
use AT to balance firing ratesDS-ATGO · CIFAR10 ResNet-19firing rate stability: 10.66% avg (Vanilla) -> 15±1.62%Improved
learned thresholds (DIET-SNN, LTMD) vs fixed thresholdDIET-SNN, LTMD · CIFAR10 ResNet-19firing rate stabilityMixed
use TGO instead of fixed SGDS-ATGO · CIFAR100 ResNet-19gradient-available proportion (%): 15.13% -> over 38.53%Improved
adjust SG width via threshold (TGO)DS-ATGO · CIFAR100 ResNet-19loss landscapeImproved
combine both adaptive threshold and SG optimization vs single-path methodsDS-ATGO · CIFAR100accuracy (%): 80.59 vs 78.84 (MPD-AGL)Improved
use DS-ATGO instead of SNN-ViT on CIFAR100 with fewer timestepsDS-ATGO · CIFAR100accuracy (%): 80.01 (T=4) -> 80.59±0.17 (T=2)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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