Image Classification on Tiny-ImageNet 200 (test) with Efficiency Tracking
55.89AccuracyPruneFuse
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PruneFuseBudget (b)=50%, Params=6.10 M, Pruning ratio (p)=0.5, Backbone=ResNet-50, Sampling Strategy=Least-Confidence2026.03 | 55.89 | 5.69 | |
| PruneFuseBudget (b)=50%, Params=2.24 M, Pruning ratio (p)=0.7, Backbone=ResNet-50, Sampling Strategy=Least-Confidence2026.03 | 55.63 | 2.09 | |
| PruneFuseBudget (b)=50%, Params=3.92 M, Pruning ratio (p)=0.6, Backbone=ResNet-50, Sampling Strategy=Least-Confidence2026.03 | 55.29 | 3.66 | |
| PruneFuseBudget (b)=50%, Params=1.02 M, Pruning ratio (p)=0.8, Backbone=ResNet-50, Sampling Strategy=Least-Confidence2026.03 | 55.18 | 0.95 | |
| Baseline (AL)Budget (b)=50%, Params=23.9 M, Backbone=ResNet-50, Sampling Strategy=Least-Confidence2026.03 | 54.65 | 22.32 |