# Image Classification on Tiny-ImageNet Bucket 1 Retain Source: [Image Classification on Tiny-ImageNet Bucket 1 Retain]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.402Z Evaluation of Image Classification performance on the specific 'Bucket 1 Retain' 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 Retain | | 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 | 84.97 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 84.9 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 84.47 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 83.85 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 83.62 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 82.93 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 81.07 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 81.06 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 80.2 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 77.91 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 77.81 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 77.61 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 77.6 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 77.1 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 77.09 | Not recorded | 69d884367d0172140ec77ba4 | ### Original Accuracy: 84.97. Result ID: 69d8c1cc47f34ce924c1f16d. [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: 84.9. Result ID: 69d8c1cc47f34ce924c1f16c. [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: 84.47. Result ID: 69d8c1cc47f34ce924c1f170. [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: 83.85. Result ID: 69d8c1cc47f34ce924c1f16f. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 83.62. Result ID: 69d8c1cc47f34ce924c1f16e. [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: 82.93. Result ID: 69d8c1cc47f34ce924c1f171. [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: 81.07. Result ID: 69d8c1cc47f34ce924c1f176. [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: 81.06. Result ID: 69d8c1cc47f34ce924c1f179. [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: 80.2. Result ID: 69d8c1cc47f34ce924c1f173. [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: 77.91. Result ID: 69d8c1cc47f34ce924c1f175. [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: 77.81. Result ID: 69d8c1cc47f34ce924c1f178. [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: 77.61. Result ID: 69d8c1cc47f34ce924c1f177. [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: 77.6. Result ID: 69d8c1cc47f34ce924c1f172. [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: 77.1. Result ID: 69d8c1cc47f34ce924c1f17a. [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: 77.09. Result ID: 69d8c1cc47f34ce924c1f174. [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. Page 1 of 1. This is an index page, not the full collection.