Image Classification on CIFAR-100 (test) (Accuracy and FLOPs)
67.87AccuracyPruneFuse
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PruneFuseBudget (b)=50%, Params=0.22 M, Pruning ratio (p)=0.5, Backbone=ResNet-56, Sampling Strategy=Least-Confidence2026.03 | 67.87 | 3.7 | |
| PruneFuseBudget (b)=50%, Params=0.14 M, Pruning ratio (p)=0.6, Backbone=ResNet-56, Sampling Strategy=Least-Confidence2026.03 | 66.89 | 2.36 | |
| PruneFuseBudget (b)=50%, Params=0.08 M, Pruning ratio (p)=0.7, Backbone=ResNet-56, Sampling Strategy=Least-Confidence2026.03 | 66.84 | 1.34 | |
| Baseline (AL)Budget (b)=50%, Params=0.86 M, Backbone=ResNet-56, Sampling Strategy=Least-Confidence2026.03 | 66.72 | 14.76 | |
| PruneFuseBudget (b)=50%, Params=0.04 M, Pruning ratio (p)=0.8, Backbone=ResNet-56, Sampling Strategy=Least-Confidence2026.03 | 65.85 | 0.6 |