Image Classification on TinyImageNet Remaining D_train_r (train)
95AccuracyRetraining
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RetrainingUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 95 | 0 | |
| RetrainingUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 93 | 0 | |
| IEU w/GAUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 92.4 | 2.6 | |
| IEU w/GAUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 91.6 | 1.3 | |
| SCRUBUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 91 | 3.9 | |
| SCRUBUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 90.9 | 2.1 | |
| IEU w/NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 90 | 5 | |
| IEU w/GA+NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 89.8 | 5.2 | |
| FTUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 89.7 | 5.2 | |
| FTUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 88.8 | 4.2 | |
| IEU w/GA+NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 88.5 | 4.5 | |
| IEU w/NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 88.1 | 4.9 | |
| RLUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 78.6 | 16.3 | |
| RLUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 76 | 17 | |
| SALUNUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 56.9 | 36.1 | |
| SALUNUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 56.3 | 38.6 |