AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

SEENN: Towards Temporal Spiking Early Exit Neural Networks

Yuhang Li, Tamar Geller, Youngeun Kim, Priyadarshini Panda

NeurIPS 2023 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 13 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 fixed timesteps with confidence-threshold early exit (SEENN-I)directly trained ResNet-19 · CIFAR-10accuracy at avg timesteps: 95.45 (T=2) -> 96.07 (1.09)Improved
SEENN-I applied to ANN-SNN conversion instead of fixed TQCFS ResNet-18 · CIFAR-10accuracy: 75.44 (T=2) -> 93.63 (1.4)Improved
use RL policy (SEENN-II) instead of confidence thresholding (SEENN-I) (ablation)SEENN · CIFAR-100 ResNet-19accuracy: 79.56 -> 80.23Improved
use RL policy (SEENN-II) instead of confidence thresholding (ablation)SEENN · CIFAR-10 ResNet-19accuracy: 96.07 -> 96.01No clear effect
SEENN-II instead of SEENN-I on ImageNet SEW-ResNet-34 (ablation)SEENN · ImageNetavg timesteps: 2.35 -> 1.79Improved
early exit on directly trained SNNTET ResNet-34 ImageNet · ImageNetaccuracy: 64.79 (6) -> 64.66 (3.38)No clear effect
early exit on CIFAR10-DVSVGG-SNN · CIFAR10-DVSaccuracy: 83.1 -> 82.7Hurt
raise confidence threshold alpha (ablation)SEENN-I · ImageNet SEW-ResNet-34share of inputs exiting at 1 timestep: 73.4% -> 30.7%Mixed
add per-timestep cross-entropy (TET loss) in SEENN-I training (ablation)SEENN-I · CIFAR/ImageNetaccuracyImproved

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