# Image Classification on Fashion-MNIST Class Unlearning (Dft) Source: [Image Classification on Fashion-MNIST Class Unlearning (Dft)]() Collection index: [llms.txt]() Data updated: 2026-05-12T08:04:05.029Z Evaluation of Image Classification performance (Accuracy) on the Fashion-MNIST Class Unlearning (Dft) dataset variant. 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) | Fashion-MNIST Class Unlearning (Dft) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Original | 92.5 | Not recorded | 68fa75ab1e209131cea69322 | | Original | 90.6 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 76.8 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 62.6 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 9.7 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 5.3 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 0.2 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 0.2 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 0 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 0 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 0 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 0 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 0 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 0 | Not recorded | 68fa75ab1e209131cea69322 | ### Original Accuracy: 92.5. Result ID: 6a02dee447f34ce924e57be6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Original Accuracy: 90.6. Result ID: 6a02dee447f34ce924e57bdf. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Finetune Accuracy: 76.8. Result ID: 6a02dee447f34ce924e57be2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Finetune Accuracy: 62.6. Result ID: 6a02dee447f34ce924e57be9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 9.7. Result ID: 6a02dee447f34ce924e57be1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 5.3. Result ID: 6a02dee447f34ce924e57be4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### BadT Accuracy: 0.2. Result ID: 6a02dee447f34ce924e57bea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 0.2. Result ID: 6a02dee447f34ce924e57beb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Retrain Accuracy: 0. Result ID: 6a02dee447f34ce924e57be0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### BadT Accuracy: 0. Result ID: 6a02dee447f34ce924e57be3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 0. Result ID: 6a02dee447f34ce924e57be5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Retrain Accuracy: 0. Result ID: 6a02dee447f34ce924e57be7. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 0. Result ID: 6a02dee447f34ce924e57be8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 0. Result ID: 6a02dee447f34ce924e57bec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.