# Image Classification on CIFAR-10 4-way sharded Source: [Image Classification on CIFAR-10 4-way sharded]() Collection index: [llms.txt]() Data updated: 2026-05-29T09:33:51.269Z Evaluation of Image Classification performance on the 4-way sharded version of the CIFAR-10 dataset. 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 4-way sharded | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 | | --- | --- | --- | --- | | Ensemble | 58.3 | Not recorded | 68fa79cd1e209131cea7f714 | | KF-Linear Conductance | 56.4 | Not recorded | 68fa79cd1e209131cea7f714 | | KF-Linear DeepLIFT | 56.2 | Not recorded | 68fa79cd1e209131cea7f714 | | KF-Linear Uniform | 52.9 | Not recorded | 68fa79cd1e209131cea7f714 | | KF-Gradient Conductance | 47.9 | Not recorded | 68fa79cd1e209131cea7f714 | | KF-Gradient DeepLIFT | 46.3 | Not recorded | 68fa79cd1e209131cea7f714 | | KF-Gradient Uniform | 45.8 | Not recorded | 68fa79cd1e209131cea7f714 | | Individual Models | 29.1 | Not recorded | 68fa79cd1e209131cea7f714 | | KD | 22.8 | Not recorded | 68fa79cd1e209131cea7f714 | | LP | 15.4 | Not recorded | 68fa79cd1e209131cea7f714 | | OTF DeepLIFT | 11.8 | Not recorded | 68fa79cd1e209131cea7f714 | | OTF Conductance | 11.4 | Not recorded | 68fa79cd1e209131cea7f714 | | OTF Uniform | 10.6 | Not recorded | 68fa79cd1e209131cea7f714 | | Vanilla Averaging | 10 | Not recorded | 68fa79cd1e209131cea7f714 | ### Ensemble Accuracy: 58.3. Result ID: 6a195d66fbc373592c14145d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### KF-Linear Conductance Accuracy: 56.4. Result ID: 6a195d66fbc373592c141465. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### KF-Linear DeepLIFT Accuracy: 56.2. Result ID: 6a195d66fbc373592c141466. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### KF-Linear Uniform Accuracy: 52.9. Result ID: 6a195d66fbc373592c141464. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### KF-Gradient Conductance Accuracy: 47.9. Result ID: 6a195d66fbc373592c141468. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### KF-Gradient DeepLIFT Accuracy: 46.3. Result ID: 6a195d66fbc373592c141469. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### KF-Gradient Uniform Accuracy: 45.8. Result ID: 6a195d66fbc373592c141467. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### Individual Models Accuracy: 29.1. Result ID: 6a195d66fbc373592c14145c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### KD Accuracy: 22.8. Result ID: 6a195d66fbc373592c14145f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400","Initialization strategy":"randomly initialized"}. This record does not assert independent reproduction. ### LP Accuracy: 15.4. Result ID: 6a195d66fbc373592c141460. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400","Initialization strategy":"weights of the first base model"}. This record does not assert independent reproduction. ### OTF DeepLIFT Accuracy: 11.8. Result ID: 6a195d66fbc373592c141463. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### OTF Conductance Accuracy: 11.4. Result ID: 6a195d66fbc373592c141462. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### OTF Uniform Accuracy: 10.6. Result ID: 6a195d66fbc373592c141461. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. ### Vanilla Averaging Accuracy: 10. Result ID: 6a195d66fbc373592c14145e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"VGG11","Fusion data points":"400"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.