# Image Classification on CIFAR-10 Bucket 1 Retain Source: [Image Classification on CIFAR-10 Bucket 1 Retain]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.190Z Evaluation of Image Classification performance on the specific 'Bucket 1' 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 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 | | --- | --- | --- | --- | | Retain-only Retain | 98.46 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 98.28 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.2 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.17 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 98.12 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 98.06 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 97.38 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 97.35 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 97.3 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 97.26 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 97.2 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 97.11 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 93.76 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 93.04 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 92.94 | Not recorded | 69d884367d0172140ec77ba4 | ### Retain-only Retain Accuracy: 98.46. Result ID: 69d8c1cc47f34ce924c1f0f7. [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: 98.28. Result ID: 69d8c1cc47f34ce924c1f0f8. [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: 98.2. Result ID: 69d8c1cc47f34ce924c1f0f4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 98.17. Result ID: 69d8c1cc47f34ce924c1f0f5. [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: 98.12. Result ID: 69d8c1cc47f34ce924c1f0f9. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"NCC","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 98.06. Result ID: 69d8c1cc47f34ce924c1f0f6. [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: 97.38. Result ID: 69d8c1cc47f34ce924c1f0fa. [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: 97.35. Result ID: 69d8c1cc47f34ce924c1f0fc. [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: 97.3. Result ID: 69d8c1cc47f34ce924c1f0fd. [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: 97.26. Result ID: 69d8c1cc47f34ce924c1f0ff. [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: 97.2. Result ID: 69d8c1cc47f34ce924c1f0fb. [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: 97.11. Result ID: 69d8c1cc47f34ce924c1f0fe. [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: 93.76. Result ID: 69d8c1cc47f34ce924c1f101. [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: 93.04. Result ID: 69d8c1cc47f34ce924c1f102. [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: 92.94. Result ID: 69d8c1cc47f34ce924c1f100. [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.