Image Classification Unlearning on CIFAR-10 50% Random Forgetting (test)
84.8AccuracySCRUB
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SCRUBBackbone=ViT2026.04 | 84.8 | 0.057 | |
| FTBackbone=ViT2026.04 | 84.1 | 0.051 | |
| IEU w/GABackbone=ViT2026.04 | 82.9 | 0.039 | |
| RetrainingBackbone=ViT2026.04 | 79 | 0 | |
| IEU w/NoisyBackbone=ViT2026.04 | 78.9 | 0.001 | |
| IEU w/GA+NoisyBackbone=ViT2026.04 | 78.7 | 0.004 | |
| RLBackbone=ViT2026.04 | 77.6 | 0.014 | |
| SALUNBackbone=ViT2026.04 | 61.6 | 0.174 |