# Image Classification on CIFAR-10 Bucket 3 Forget Source: [Image Classification on CIFAR-10 Bucket 3 Forget]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.270Z Evaluation of Image Classification performance on the specific 'Bucket 3' subset of CIFAR-10 used for forgetting analysis, reporting standard Accuracy. 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 Bucket 3 Forget | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 | 98.29 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.22 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.15 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 97.35 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 94.51 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 68.07 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 66.69 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 56.75 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 52.3 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 49.97 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 49.31 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 48.5 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 48.08 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 46.83 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 0 | Not recorded | 69d884367d0172140ec77ba4 | ### Original Accuracy: 98.29. Result ID: 69d8c1cc47f34ce924c1f121. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 98.22. Result ID: 69d8c1cc47f34ce924c1f122. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Linear Probe","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 98.15. Result ID: 69d8c1cc47f34ce924c1f123. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"NCC","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Retain-only Retain Accuracy: 97.35. Result ID: 69d8c1cc47f34ce924c1f125. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Linear Probe","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Retain-only Retain Accuracy: 94.51. Result ID: 69d8c1cc47f34ce924c1f126. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"NCC","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Salun with CMF Accuracy: 68.07. Result ID: 69d8c1cc47f34ce924c1f12b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"Linear Probe","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Random-label with CMF Accuracy: 66.69. Result ID: 69d8c1cc47f34ce924c1f128. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"Linear Probe","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### NegGrad+ with CMF Accuracy: 56.75. Result ID: 69d8c1cc47f34ce924c1f12e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"Linear Probe","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Salun with CMF Accuracy: 52.3. Result ID: 69d8c1cc47f34ce924c1f12c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"NCC","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Random-label with CMF Accuracy: 49.97. Result ID: 69d8c1cc47f34ce924c1f129. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"NCC","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Salun with CMF Accuracy: 49.31. Result ID: 69d8c1cc47f34ce924c1f12a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### NegGrad+ with CMF Accuracy: 48.5. Result ID: 69d8c1cc47f34ce924c1f12d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### NegGrad+ with CMF Accuracy: 48.08. Result ID: 69d8c1cc47f34ce924c1f12f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"NCC","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Random-label with CMF Accuracy: 46.83. Result ID: 69d8c1cc47f34ce924c1f127. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Retain-only Retain Accuracy: 0. Result ID: 69d8c1cc47f34ce924c1f124. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.