# Image Classification on CIFAR-100 Bucket 10 Forget Source: [Image Classification on CIFAR-100 Bucket 10 Forget]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.376Z Evaluation of Image Classification performance on the specific 'Bucket 10 Forget' subset of CIFAR-100, 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-100 Bucket 10 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 | 90.32 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 90.08 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 89.58 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 87.82 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 81.88 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 53.06 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 52.54 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 47.08 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 46.4 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 46.34 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 45.28 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 41.1 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 34.7 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 22.3 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 0 | Not recorded | 69d884367d0172140ec77ba4 | ### Original Accuracy: 90.32. Result ID: 69d8c1cc47f34ce924c1f15d. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 90.08. Result ID: 69d8c1cc47f34ce924c1f15e. [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: 89.58. Result ID: 69d8c1cc47f34ce924c1f15f. [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: 87.82. Result ID: 69d8c1cc47f34ce924c1f161. [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: 81.88. Result ID: 69d8c1cc47f34ce924c1f162. [Reporting 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: 53.06. Result ID: 69d8c1cc47f34ce924c1f163. [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. ### Random-label with CMF Accuracy: 52.54. Result ID: 69d8c1cc47f34ce924c1f165. [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. ### NegGrad+ with CMF Accuracy: 47.08. Result ID: 69d8c1cc47f34ce924c1f169. [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. ### Salun with CMF Accuracy: 46.4. Result ID: 69d8c1cc47f34ce924c1f166. [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. ### Salun with CMF Accuracy: 46.34. Result ID: 69d8c1cc47f34ce924c1f168. [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. ### NegGrad+ with CMF Accuracy: 45.28. Result ID: 69d8c1cc47f34ce924c1f16b. [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: 41.1. Result ID: 69d8c1cc47f34ce924c1f164. [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: 34.7. Result ID: 69d8c1cc47f34ce924c1f167. [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: 22.3. Result ID: 69d8c1cc47f34ce924c1f16a. [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. ### Retain-only Retain Accuracy: 0. Result ID: 69d8c1cc47f34ce924c1f160. [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.