AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Temporal Representation Enhancement (TRE): Learning to Forget Dominant Patterns for Enhanced Temporal Spiking Features

Wei Liu, Li Yang, Yufei Wang, Han Xiao, Boyu Cai, Weiming Hu

CVPR 2026 · Architectures and efficiency › Spiking networks · approach: Spiking transformers

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 TRE channel suppression to baseline training (ablation)spiking ResNet-19 · CIFAR-100, T=4accuracy (%): 77.75 -> 81.27Improved
add TRE channel suppression to baseline training (ablation)spiking ResNet-19 · DVS-CIFAR10, T=10accuracy (%): 78.40 -> 83.60Improved
use TRE instead of TET supervision (ablation)spiking ResNet-19 · CIFAR-100, T=4accuracy (%): 80.16 -> 81.27Improved
use TRE instead of TET supervision (ablation)spiking ResNet-19 · DVS-CIFAR10, T=10accuracy (%): 83.00 -> 83.60Improved
use adaptive threshold gating instead of rank-based top-1 gating (ablation)TRE · CIFAR-100, T=4accuracy (%): 80.88 -> 81.27Improved
suppress more channels with top-k gating (k=1 to 4) (ablation)TRE · CIFAR-100, T=4accuracy (%): 80.88 -> 80.52Hurt
add TRE to PSN ResNet-34PSN · ImageNet, T=4top-1 accuracy (%): 70.54 -> 71.60Improved
add TRE to PSN ResNet-18PSN · ImageNet, T=4top-1 accuracy (%): 67.63 -> 67.74No clear effect
add TRE to PSN ResNet-34PSN · ImageNet, T=4mean off-diagonal cosine similarity: 0.95 -> 0.85Improved
set adaptive scale lambda to 0.0 with theta0 0.05 (ablation)TRE · CIFAR-100, T=4accuracy (%): 81.27 -> 80.76Hurt
increase fixed threshold theta0 from 0.05 to 0.06 (ablation)TRE · CIFAR-100, T=4accuracy (%): 81.27 -> 80.85Hurt
add normalized gating during training (ablation)TRE · CIFAR-100classification score distribution shiftImproved

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