# Image Classification on Tiny-ImageNet Bucket 20 Forget Source: [Image Classification on Tiny-ImageNet Bucket 20 Forget]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.471Z Evaluation of Image Classification performance on the specific 'Bucket 20 Forget' subset of the Tiny-ImageNet dataset, reporting 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) | Tiny-ImageNet Bucket 20 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 | 85.68 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 85.44 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 84.7 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 81.44 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 78.64 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 75.24 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 71.04 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 68.66 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 67.62 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 62.56 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 60.48 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 33.98 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 31.24 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 27.58 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 0 | Not recorded | 69d884367d0172140ec77ba4 | ### Original Accuracy: 85.68. Result ID: 69d8c1cc47f34ce924c1f19a. [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: 85.44. Result ID: 69d8c1cc47f34ce924c1f199. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 84.7. Result ID: 69d8c1cc47f34ce924c1f19b. [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: 81.44. Result ID: 69d8c1cc47f34ce924c1f19d. [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: 78.64. Result ID: 69d8c1cc47f34ce924c1f19e. [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: 75.24. Result ID: 69d8c1cc47f34ce924c1f1a3. [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: 71.04. Result ID: 69d8c1cc47f34ce924c1f1a0. [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: 68.66. Result ID: 69d8c1cc47f34ce924c1f1a2. [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: 67.62. Result ID: 69d8c1cc47f34ce924c1f1a4. [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: 62.56. Result ID: 69d8c1cc47f34ce924c1f19f. [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: 60.48. Result ID: 69d8c1cc47f34ce924c1f1a1. [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: 33.98. Result ID: 69d8c1cc47f34ce924c1f1a6. [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: 31.24. Result ID: 69d8c1cc47f34ce924c1f1a5. [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: 27.58. Result ID: 69d8c1cc47f34ce924c1f1a7. [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. ### Retain-only Retain Accuracy: 0. Result ID: 69d8c1cc47f34ce924c1f19c. [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.