Event Data Classification On Cifar10 Dvs 1
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| OTTT | 77.1 | Online Training Through Time for Spiking Neural Networks | - |
| STS-ResNet | 69.2 | Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction | - |
| ECSNet | 72.7 | Ecsnet: Spatio-temporal feature learning for event camera | |
| tdBN + NDA (VGG11) | 81.7 | Neuromorphic Data Augmentation for Training Spiking Neural Networks | - |
| IM-Loss (ResNet-19) | 72.60 | IM-Loss: Information Maximization Loss for Spiking Neural Networks | - |
| STL-SNN | 78.50 | A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networks | - |
| Dspike (ResNet-18) | 75.4 | Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks | - |
0 of 7 row(s) selected.