# Image Classification on CIFAR-10 Sample Unlearning (Df) Source: [Image Classification on CIFAR-10 Sample Unlearning (Df)]() Collection index: [llms.txt]() Data updated: 2026-05-12T08:04:04.659Z Evaluation of standard Image Classification accuracy on the CIFAR-10 dataset variant specifically designed for Sample Unlearning evaluation (Df). 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) | CIFAR-10 Sample Unlearning (Df) | | 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 | 100 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 100 | Not recorded | 68fa75ab1e209131cea69322 | | Original | 100 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 100 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 100 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 99.22 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 99.22 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 99.22 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 99.22 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 98.44 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 98.44 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 97.66 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 96.88 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 82.81 | Not recorded | 68fa75ab1e209131cea69322 | ### Original Accuracy: 100. Result ID: 6a02dee447f34ce924e57b37. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Finetune Accuracy: 100. Result ID: 6a02dee447f34ce924e57b3a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Original Accuracy: 100. Result ID: 6a02dee447f34ce924e57b3e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Finetune Accuracy: 100. Result ID: 6a02dee447f34ce924e57b41. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 100. Result ID: 6a02dee447f34ce924e57b43. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 99.22. Result ID: 6a02dee447f34ce924e57b39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 99.22. Result ID: 6a02dee447f34ce924e57b3c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Retrain Accuracy: 99.22. Result ID: 6a02dee447f34ce924e57b3f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 99.22. Result ID: 6a02dee447f34ce924e57b44. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 98.44. Result ID: 6a02dee447f34ce924e57b40. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### BadT Accuracy: 98.44. Result ID: 6a02dee447f34ce924e57b42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 97.66. Result ID: 6a02dee447f34ce924e57b3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Retrain Accuracy: 96.88. Result ID: 6a02dee447f34ce924e57b38. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### BadT Accuracy: 82.81. Result ID: 6a02dee447f34ce924e57b3b. [Reporting paper]() [Method origin paper]() 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.