AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Neuromorphic Data Augmentation for Training Spiking Neural Networks

Yuhang Li, Youngeun Kim, Hyoungseob Park, Tamar Geller, Priyadarshini Panda

ECCV 2022 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 85 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 geometric NDA (M1N2) to tdBN trainingtdBN ResNet-19 · CIFAR10-DVStop-1 accuracy: 67.9 -> 78.0Improved
add geometric NDA to tdBN trainingtdBN ResNet-19 · N-Caltech 101top-1 accuracy: 62.8 -> 78.6Improved
add NDA to tdBN trainingtdBN ResNet-19 · N-Carstop-1 accuracy: 82.4 -> 87.2Improved
add NDA to tdBN trainingtdBN VGG-11 (128x128) · CIFAR10-DVStop-1 accuracy: 76.3 -> 81.7Improved
use geometric instead of photometric/color augmentation (ablation)NDA ResNet-19 · CIFAR10-DVStop-1 accuracy: 62.8 -> 78.0Improved
use geometric instead of photometric/color augmentation (ablation)NDA ResNet-19 · N-Caltech101top-1 accuracy: 64.0 -> 78.6Improved
increase augmentation intensity/number from M1N2 to M3N3 (ablation)NDA ResNet-19 · CIFAR10-DVStop-1 accuracy: 78.0 -> 71.4Hurt
increase augmentation intensity/number from M1N2 to M3N3 (ablation)NDA ResNet-19 · N-Caltech101top-1 accuracy: 78.6 -> 65.1Hurt
lower intensity from M1N2 to M1N1 (ablation)NDA ResNet-19 · CIFAR10-DVStop-1 accuracy: 78.0 -> 73.4Hurt
add NDA to trainingtdBN ResNet-19 · CIFAR10-DVS weight noise N(0,0.01)accuracy drop: 19.4% drop -> 1.5% dropImproved
add NDA to trainingtdBN ResNet-19 · CIFAR10-DVS weight noise N(0,0.02)accuracy drop: 43.4% drop -> 11.3% dropImproved
supervised pre-training on N-Caltech101 before finetuningVGG-11 · CIFAR10-DVStop-1 accuracy: 81.7 -> 80.9No 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