# Image Classification on TinyImageNet Forgotten (train) Source: [Image Classification on TinyImageNet Forgotten (train)]() Collection index: [llms.txt]() Data updated: 2026-04-13T09:47:26.673Z Evaluation of Image Classification performance on the training split of the TinyImageNet Forgotten dataset, reporting Accuracy and Performance Gap. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Image Classification | | Dataset (including any stated split) | TinyImageNet Forgotten (train) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [Performance Gap](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SCRUB | 64.2 | Not recorded | 69dc789f7d0172140ec78bd0 | | SCRUB | 63.2 | Not recorded | 69dc789f7d0172140ec78bd0 | | FT | 60.9 | Not recorded | 69dc789f7d0172140ec78bd0 | | FT | 59.5 | Not recorded | 69dc789f7d0172140ec78bd0 | | IEU w/GA | 54.7 | Not recorded | 69dc789f7d0172140ec78bd0 | | RL | 52.5 | Not recorded | 69dc789f7d0172140ec78bd0 | | IEU w/GA | 52.5 | Not recorded | 69dc789f7d0172140ec78bd0 | | IEU w/GA+Noisy | 51.8 | Not recorded | 69dc789f7d0172140ec78bd0 | | RL | 51.2 | Not recorded | 69dc789f7d0172140ec78bd0 | | IEU w/Noisy | 50.8 | Not recorded | 69dc789f7d0172140ec78bd0 | | SALUN | 50.7 | Not recorded | 69dc789f7d0172140ec78bd0 | | IEU w/GA+Noisy | 48.6 | Not recorded | 69dc789f7d0172140ec78bd0 | | IEU w/Noisy | 48.3 | Not recorded | 69dc789f7d0172140ec78bd0 | | Retraining | 47 | Not recorded | 69dc789f7d0172140ec78bd0 | | SALUN | 45.4 | Not recorded | 69dc789f7d0172140ec78bd0 | | Retraining | 42.9 | Not recorded | 69dc789f7d0172140ec78bd0 | ### SCRUB Accuracy: 64.2. Result ID: 69dcbb9847f34ce924c41141. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 63.2. Result ID: 69dcbb9847f34ce924c41149. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### FT Accuracy: 60.9. Result ID: 69dcbb9847f34ce924c4113f. [Reporting paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### FT Accuracy: 59.5. Result ID: 69dcbb9847f34ce924c41147. [Reporting paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### IEU w/GA Accuracy: 54.7. Result ID: 69dcbb9847f34ce924c41143. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### RL Accuracy: 52.5. Result ID: 69dcbb9847f34ce924c41148. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### IEU w/GA Accuracy: 52.5. Result ID: 69dcbb9847f34ce924c4114b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### IEU w/GA+Noisy Accuracy: 51.8. Result ID: 69dcbb9847f34ce924c41145. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### RL Accuracy: 51.2. Result ID: 69dcbb9847f34ce924c41140. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### IEU w/Noisy Accuracy: 50.8. Result ID: 69dcbb9847f34ce924c41144. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### SALUN Accuracy: 50.7. Result ID: 69dcbb9847f34ce924c41142. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### IEU w/GA+Noisy Accuracy: 48.6. Result ID: 69dcbb9847f34ce924c4114d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### IEU w/Noisy Accuracy: 48.3. Result ID: 69dcbb9847f34ce924c4114c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### Retraining Accuracy: 47. Result ID: 69dcbb9847f34ce924c4113e. [Reporting paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"30%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### SALUN Accuracy: 45.4. Result ID: 69dcbb9847f34ce924c4114a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. ### Retraining Accuracy: 42.9. Result ID: 69dcbb9847f34ce924c41146. [Reporting paper]() Recorded evaluation configuration: {"Unlearning Scenario":"Random Data Forgetting","Forgetting Ratio":"50%","Backbone":"ResNet"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.