# Image Classification on Tiny-ImageNet Bucket 1 Forget Source: [Image Classification on Tiny-ImageNet Bucket 1 Forget]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.425Z Evaluation of Image Classification performance on the specific 'Bucket 1 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 1 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 | 81.2 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 80.4 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 79.2 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 77.6 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 74.8 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 74.4 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 68.4 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 68 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 64 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 61.6 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 61.2 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 34.4 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 17.2 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 12 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 0 | Not recorded | 69d884367d0172140ec77ba4 | ### Original Accuracy: 81.2. Result ID: 69d8c1cc47f34ce924c1f17c. [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: 80.4. Result ID: 69d8c1cc47f34ce924c1f17d. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"NCC","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 79.2. Result ID: 69d8c1cc47f34ce924c1f17b. [Reporting 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: 77.6. Result ID: 69d8c1cc47f34ce924c1f17f. [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: 74.8. Result ID: 69d8c1cc47f34ce924c1f180. [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: 74.4. Result ID: 69d8c1cc47f34ce924c1f185. [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: 68.4. Result ID: 69d8c1cc47f34ce924c1f182. [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. Result ID: 69d8c1cc47f34ce924c1f184. [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: 64. Result ID: 69d8c1cc47f34ce924c1f186. [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: 61.6. Result ID: 69d8c1cc47f34ce924c1f181. [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: 61.2. Result ID: 69d8c1cc47f34ce924c1f183. [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: 34.4. Result ID: 69d8c1cc47f34ce924c1f188. [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: 17.2. Result ID: 69d8c1cc47f34ce924c1f187. [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: 12. Result ID: 69d8c1cc47f34ce924c1f189. [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: 69d8c1cc47f34ce924c1f17e. [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.