# Image Classification on CIFAR-10 Class Unlearning (Drt) Source: [Image Classification on CIFAR-10 Class Unlearning (Drt)]() Collection index: [llms.txt]() Data updated: 2026-05-12T08:04:04.897Z Evaluation of standard Image Classification utility (Accuracy) on the CIFAR-10 dataset variant specifically configured for Class Unlearning experiments, denoted as (Drt). 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 Class Unlearning (Drt) | | Metric | Accuracy (Drt) | | 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 (Drt)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Drt) | Result date | Report paper | | --- | --- | --- | --- | | Residual Feature Alignment Unlearning | 98.72 | Not recorded | 68fa75ab1e209131cea69322 | | Original | 98.64 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 98.64 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 98.56 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 98.49 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 98.43 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 95.89 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 95.73 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 95.69 | Not recorded | 68fa75ab1e209131cea69322 | | Original | 95.64 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 95.52 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 95.38 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 80.62 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 36.33 | Not recorded | 68fa75ab1e209131cea69322 | ### Residual Feature Alignment Unlearning Accuracy (Drt): 98.72. Result ID: 6a02dee447f34ce924e57ba6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Original Accuracy (Drt): 98.64. Result ID: 6a02dee447f34ce924e57ba0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Retrain Accuracy (Drt): 98.64. Result ID: 6a02dee447f34ce924e57ba1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### BadT Accuracy (Drt): 98.56. Result ID: 6a02dee447f34ce924e57ba4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Finetune Accuracy (Drt): 98.49. Result ID: 6a02dee447f34ce924e57ba3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### SCRUB Accuracy (Drt): 98.43. Result ID: 6a02dee447f34ce924e57ba5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Retrain Accuracy (Drt): 95.89. Result ID: 6a02dee447f34ce924e57b9a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### SCRUB Accuracy (Drt): 95.73. Result ID: 6a02dee447f34ce924e57b9e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Finetune Accuracy (Drt): 95.69. Result ID: 6a02dee447f34ce924e57b9c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Original Accuracy (Drt): 95.64. Result ID: 6a02dee447f34ce924e57b99. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy (Drt): 95.52. Result ID: 6a02dee447f34ce924e57b9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### BadT Accuracy (Drt): 95.38. Result ID: 6a02dee447f34ce924e57b9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### NegGrad Accuracy (Drt): 80.62. Result ID: 6a02dee447f34ce924e57b9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### NegGrad Accuracy (Drt): 36.33. Result ID: 6a02dee447f34ce924e57ba2. [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.