# Image Classification on CIFAR-10 Class Unlearning (Dr) Source: [Image Classification on CIFAR-10 Class Unlearning (Dr)]() Collection index: [llms.txt]() Data updated: 2026-05-12T08:04:04.833Z Evaluation of standard Image Classification utility (Accuracy) on the CIFAR-10 dataset variant specifically configured for Class Unlearning experiments, denoted as (Dr). 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 (Dr) | | 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 | | Retrain | 100 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 100 | Not recorded | 68fa75ab1e209131cea69322 | | Original | 100 | Not recorded | 68fa75ab1e209131cea69322 | | Retrain | 100 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 100 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 99.99 | Not recorded | 68fa75ab1e209131cea69322 | | Residual Feature Alignment Unlearning | 99.99 | Not recorded | 68fa75ab1e209131cea69322 | | BadT | 99.99 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 99.99 | Not recorded | 68fa75ab1e209131cea69322 | | Finetune | 99.98 | Not recorded | 68fa75ab1e209131cea69322 | | SCRUB | 99.97 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 84.54 | Not recorded | 68fa75ab1e209131cea69322 | | NegGrad | 37.34 | Not recorded | 68fa75ab1e209131cea69322 | ### Original Accuracy: 100. Result ID: 6a02dee447f34ce924e57b7d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Retrain Accuracy: 100. Result ID: 6a02dee447f34ce924e57b7e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Finetune Accuracy: 100. Result ID: 6a02dee447f34ce924e57b80. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Original Accuracy: 100. Result ID: 6a02dee447f34ce924e57b84. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Retrain Accuracy: 100. Result ID: 6a02dee447f34ce924e57b85. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 100. Result ID: 6a02dee447f34ce924e57b8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### BadT Accuracy: 99.99. Result ID: 6a02dee447f34ce924e57b81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### Residual Feature Alignment Unlearning Accuracy: 99.99. Result ID: 6a02dee447f34ce924e57b83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### BadT Accuracy: 99.99. Result ID: 6a02dee447f34ce924e57b88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 99.99. Result ID: 6a02dee447f34ce924e57b89. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Finetune Accuracy: 99.98. Result ID: 6a02dee447f34ce924e57b87. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### SCRUB Accuracy: 99.97. Result ID: 6a02dee447f34ce924e57b82. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 84.54. Result ID: 6a02dee447f34ce924e57b7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### NegGrad Accuracy: 37.34. Result ID: 6a02dee447f34ce924e57b86. [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.