OTTT

Reported on 5 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision5 results

Gesture RecognitiononDVS128 Gesture
Accuracy (%)· 2022-10-09
96.88
best: 100 (TENNs-PLEIADES)
Online Training Through Time for Spiking Neural Networks arXiv:2210.04195
Image ClassificationonFashion-MNIST
Percentage error· 2022-10-09
9.6
best: 3.64 (PreAct-ResNet18 + FMix)
Online Training Through Time for Spiking Neural Networks arXiv:2210.04195
Image ClassificationonCIFAR-10
Percentage correct· 2022-10-09
93.73
best: 99.5 (ViT-H/14)
Online Training Through Time for Spiking Neural Networks arXiv:2210.04195
Image ClassificationonCIFAR-100
Percentage correct· 2022-10-09
71.05
best: 96.08 (EffNet-L2 (SAM))
Online Training Through Time for Spiking Neural Networks arXiv:2210.04195
Event data classificationonCIFAR10-DVS
Accuracy· 2022-10-09
77.1
best: 81.7 (tdBN + NDA (VGG11))
Online Training Through Time for Spiking Neural Networks arXiv:2210.04195