# Image Classification on CIFAR-10 Bucket 3 Retain Source: [Image Classification on CIFAR-10 Bucket 3 Retain]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.247Z Evaluation of Image Classification performance on the specific 'Bucket 3' subset of the CIFAR-10 Retain 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) | CIFAR-10 Bucket 3 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 | | --- | --- | --- | --- | | Retain-only Retain | 98.61 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 98.17 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.16 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.15 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.02 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 97.98 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 96.94 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 96.81 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 96.78 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 96.66 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 96.23 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 96.19 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 93.68 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 93.45 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 93.41 | Not recorded | 69d884367d0172140ec77ba4 | ### Retain-only Retain Accuracy: 98.61. Result ID: 69d8c1cc47f34ce924c1f115. [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: 98.17. Result ID: 69d8c1cc47f34ce924c1f116. [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: 98.16. Result ID: 69d8c1cc47f34ce924c1f112. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 98.15. Result ID: 69d8c1cc47f34ce924c1f113. [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: 98.02. Result ID: 69d8c1cc47f34ce924c1f114. [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: 97.98. Result ID: 69d8c1cc47f34ce924c1f117. [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: 96.94. Result ID: 69d8c1cc47f34ce924c1f11b. [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: 96.81. Result ID: 69d8c1cc47f34ce924c1f11d. [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: 96.78. Result ID: 69d8c1cc47f34ce924c1f118. [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: 96.66. Result ID: 69d8c1cc47f34ce924c1f11a. [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: 96.23. Result ID: 69d8c1cc47f34ce924c1f11c. [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: 96.19. Result ID: 69d8c1cc47f34ce924c1f119. [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: 93.68. Result ID: 69d8c1cc47f34ce924c1f11f. [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: 93.45. Result ID: 69d8c1cc47f34ce924c1f120. [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: 93.41. Result ID: 69d8c1cc47f34ce924c1f11e. [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. Page 1 of 1. This is an index page, not the full collection.