# Image Classification on Fashion-MNIST Sample Unlearning (Dt) Source: [Image Classification on Fashion-MNIST Sample Unlearning (Dt)]() Collection index: [llms.txt]() Data updated: 2026-05-12T08:04:04.795Z Evaluation of model utility (Accuracy) for Image Classification tasks performed on the specific 'Fashion-MNIST Sample Unlearning (Dt)' 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 Sample Unlearning (Dt) | | 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 | | --- | --- | --- | --- | | Retrain | 95.35 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 95.29 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 95.23 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 95.11 | Not recorded | 68fa75ab1e209131cea69322 | | Original | 95.06 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 94.99 | Not recorded | 68fa75ab1e209131cea69322 | | Original | 94.98 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 94.88 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 94.85 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 94.84 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 94.77 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 94.65 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 94.63 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 94.5 | Not recorded | 68fa75ab1e209131cea69322 | ### Retrain Accuracy: 95.35. Result ID: 6a02dee447f34ce924e57b77. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 95.29. Result ID: 6a02dee447f34ce924e57b7b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Finetune Accuracy: 95.23. Result ID: 6a02dee447f34ce924e57b79. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### BadT Accuracy: 95.11. Result ID: 6a02dee447f34ce924e57b7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Original Accuracy: 95.06. Result ID: 6a02dee447f34ce924e57b76. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 94.99. Result ID: 6a02dee447f34ce924e57b7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Original Accuracy: 94.98. Result ID: 6a02dee447f34ce924e57b6f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 94.88. Result ID: 6a02dee447f34ce924e57b78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 94.85. Result ID: 6a02dee447f34ce924e57b75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Retrain Accuracy: 94.84. Result ID: 6a02dee447f34ce924e57b70. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Finetune Accuracy: 94.77. Result ID: 6a02dee447f34ce924e57b72. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 94.65. Result ID: 6a02dee447f34ce924e57b71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### BadT Accuracy: 94.63. Result ID: 6a02dee447f34ce924e57b73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 94.5. Result ID: 6a02dee447f34ce924e57b74. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.