# Image Classification on CIFAR-100 Bucket 1 Retain Source: [Image Classification on CIFAR-100 Bucket 1 Retain]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:24:36.294Z Evaluation of Image Classification performance on the specific 'Bucket 1 Retain' subset of the CIFAR-100 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-100 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 | 90.32 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 90.09 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 89.95 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 89.93 | Not recorded | 69d884367d0172140ec77ba4 | | Original | 89.62 | Not recorded | 69d884367d0172140ec77ba4 | | Retain-only Retain | 89.24 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 86.99 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 86.97 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 86.2 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 86.2 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 85.53 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 85.48 | Not recorded | 69d884367d0172140ec77ba4 | | Random-label with CMF | 84.79 | Not recorded | 69d884367d0172140ec77ba4 | | NegGrad+ with CMF | 83.47 | Not recorded | 69d884367d0172140ec77ba4 | | Salun with CMF | 83.43 | Not recorded | 69d884367d0172140ec77ba4 | ### Retain-only Retain Accuracy: 90.32. Result ID: 69d8c1cc47f34ce924c1f134. [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: 90.09. Result ID: 69d8c1cc47f34ce924c1f130. [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: 89.95. Result ID: 69d8c1cc47f34ce924c1f133. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Head":"Output","Backbone":"ViT-S/16","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### Original Accuracy: 89.93. Result ID: 69d8c1cc47f34ce924c1f131. [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: 89.62. Result ID: 69d8c1cc47f34ce924c1f132. [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: 89.24. Result ID: 69d8c1cc47f34ce924c1f135. [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: 86.99. Result ID: 69d8c1cc47f34ce924c1f136. [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: 86.97. Result ID: 69d8c1cc47f34ce924c1f138. [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: 86.2. Result ID: 69d8c1cc47f34ce924c1f139. [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: 86.2. Result ID: 69d8c1cc47f34ce924c1f13b. [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: 85.53. Result ID: 69d8c1cc47f34ce924c1f13e. [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: 85.48. Result ID: 69d8c1cc47f34ce924c1f13c. [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: 84.79. Result ID: 69d8c1cc47f34ce924c1f137. [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: 83.47. Result ID: 69d8c1cc47f34ce924c1f13d. [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: 83.43. Result ID: 69d8c1cc47f34ce924c1f13a. [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. Page 1 of 1. This is an index page, not the full collection.