Image Classification on CIFAR-10 (test) (Top-1 Accuracy Change)
1.77Top-1 Accuracy ChangeNC-CTD
Evaluation results
| Method | Links | |
|---|---|---|
| NC-CTDBackbone=ResNet-34, Compression Rate=0.322026.05 | 1.77 | |
| Method in [35]Backbone=ResNet-34, Compression Rate=0.52026.05 | 0.19 | |
| APSSFBackbone=ResNet-34, Compression Rate=0.52026.05 | 0.02 | |
| Slice-wise Feature DistillationBackbone=ResNet-34, Compression Rate=0.52026.05 | -0.34 | |
| Method in [35]Backbone=ResNet-34, Compression Rate=0.72026.05 | -0.8 | |
| LJSVDBackbone=ResNet-34, Compression Rate=0.952026.05 | -1.14 | |
| Slice-wise Feature DistillationBackbone=ResNet-34, Compression Rate=0.72026.05 | -5.85 |