Image Classification on TinyImageNet D (test)
57AccuracySCRUB
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SCRUBUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 57 | 2.4 | |
| FTUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 56.2 | 1.5 | |
| SCRUBUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 55.6 | 6.1 | |
| RetrainingUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 54.6 | 0 | |
| IEU w/GAUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 54.1 | 0.5 | |
| IEU w/NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 54 | 0.6 | |
| FTUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 53.8 | 4.3 | |
| IEU w/GA+NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 53.6 | 1 | |
| RLUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 52.2 | 2.4 | |
| RLUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 50.7 | 1.3 | |
| RetrainingUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 49.5 | 0 | |
| IEU w/GA+NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 49.5 | 0 | |
| IEU w/GAUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 49.4 | 0.1 | |
| IEU w/NoisyUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 49.4 | 0 | |
| SALUNUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=30%, Backbone=ResNet2026.04 | 48.6 | 6 | |
| SALUNUnlearning Scenario=Random Data Forgetting, Forgetting Ratio=50%, Backbone=ResNet2026.04 | 44.6 | 4.9 |