# Image Classification on CIFAR-10 FedAvg with 50 clients, beta=0.5 non-IID (test) Source: [Image Classification on CIFAR-10 FedAvg with 50 clients, beta=0.5 non-IID (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:25.706Z Evaluation of Image Classification performance on the CIFAR-10 dataset under a federated learning setting using 50 clients, employing a non-IID data distribution parameterized by beta=0.5, measured on the test set. 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 FedAvg with 50 clients, beta=0.5 non-IID (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | | --- | --- | --- | --- | | OnDev-LCT-8/1 | 78.28 | Not recorded | 68fa77951e209131cea7425c | | OnDev-LCT-2/1 | 78.2 | Not recorded | 68fa77951e209131cea7425c | | OnDev-LCT-4/1 | 77.68 | Not recorded | 68fa77951e209131cea7425c | | OnDev-LCT-1/1 | 76.93 | Not recorded | 68fa77951e209131cea7425c | | CCT-4/2 | 69.82 | Not recorded | 68fa77951e209131cea7425c | | CCT-2/2 | 68.87 | Not recorded | 68fa77951e209131cea7425c | | Hybrid Vision Transformer (ViT) | 65.7 | Not recorded | 68fa77951e209131cea7425c | | Hybrid Vision Performer (ViP) | 65.53 | Not recorded | 68fa77951e209131cea7425c | | Hybrid Vision Nyströformer (ViN) | 63.81 | Not recorded | 68fa77951e209131cea7425c | | Hybrid Vision Linformer (ViL) | 49.01 | Not recorded | 68fa77951e209131cea7425c | | MobileViTv2-0.5 | 48.95 | Not recorded | 68fa77951e209131cea7425c | | MobileViT-XXS | 45.91 | Not recorded | 68fa77951e209131cea7425c | | EdgeNeXt-XXS | 45.24 | Not recorded | 68fa77951e209131cea7425c | ### OnDev-LCT-8/1 Accuracy: 78.28. Result ID: 699546ed3badfaffe6355161. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"0.91M"}. This record does not assert independent reproduction. ### OnDev-LCT-2/1 Accuracy: 78.2. Result ID: 699546ed3badfaffe635515f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"0.31M"}. This record does not assert independent reproduction. ### OnDev-LCT-4/1 Accuracy: 77.68. Result ID: 699546ed3badfaffe6355160. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"0.51M"}. This record does not assert independent reproduction. ### OnDev-LCT-1/1 Accuracy: 76.93. Result ID: 699546ed3badfaffe635515e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"0.21M"}. This record does not assert independent reproduction. ### CCT-4/2 Accuracy: 69.82. Result ID: 699546ed3badfaffe6355159. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"0.48M"}. This record does not assert independent reproduction. ### CCT-2/2 Accuracy: 68.87. Result ID: 699546ed3badfaffe6355158. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"0.28M"}. This record does not assert independent reproduction. ### Hybrid Vision Transformer (ViT) Accuracy: 65.7. Result ID: 699546ed3badfaffe635515a. [Reporting paper]() Recorded evaluation configuration: {"#Params":"0.75M"}. This record does not assert independent reproduction. ### Hybrid Vision Performer (ViP) Accuracy: 65.53. Result ID: 699546ed3badfaffe635515b. [Reporting paper]() Recorded evaluation configuration: {"#Params":"0.76M"}. This record does not assert independent reproduction. ### Hybrid Vision Nyströformer (ViN) Accuracy: 63.81. Result ID: 699546ed3badfaffe635515d. [Reporting paper]() Recorded evaluation configuration: {"#Params":"0.76M"}. This record does not assert independent reproduction. ### Hybrid Vision Linformer (ViL) Accuracy: 49.01. Result ID: 699546ed3badfaffe635515c. [Reporting paper]() Recorded evaluation configuration: {"#Params":"0.95M"}. This record does not assert independent reproduction. ### MobileViTv2-0.5 Accuracy: 48.95. Result ID: 699546ed3badfaffe6355157. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"1.13M"}. This record does not assert independent reproduction. ### MobileViT-XXS Accuracy: 45.91. Result ID: 699546ed3badfaffe6355156. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"0.94M"}. This record does not assert independent reproduction. ### EdgeNeXt-XXS Accuracy: 45.24. Result ID: 699546ed3badfaffe6355155. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"1.17M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.