# Image Classification on CIFAR-10 Dir(0.5) (New Clients) (Corruption Robustness) Source: [Image Classification on CIFAR-10 Dir(0.5) (New Clients) (Corruption Robustness)]() Collection index: [llms.txt]() Data updated: 2026-03-13T08:12:28.429Z Evaluation of Image Classification performance on CIFAR-10 data partitioned using a Dirichlet distribution (alpha=0.5) across new clients, measured across various image corruption levels (e.g., motion blur, fog, noise). 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 Dir(0.5) (New Clients) | | Metric | Accuracy (Clean) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 (Clean)](): Higher is better; unit: PERCENT. - [Accuracy (Motion Blur)](): Higher is better; unit: PERCENT. - [Accuracy (Defocus Blur)](): Higher is better; unit: PERCENT. - [Accuracy (Gaussian Noise)](): Higher is better; unit: PERCENT. - [Accuracy (Shot Noise)](): Higher is better; unit: PERCENT. - [Accuracy (Impulse Noise)](): Higher is better; unit: PERCENT. - [Accuracy (Frost)](): Higher is better; unit: PERCENT. - [Accuracy (Fog)](): Higher is better; unit: PERCENT. - [Accuracy (JPEG Compression)](): Higher is better; unit: PERCENT. - [Accuracy (Brightness)](): Higher is better; unit: PERCENT. - [Accuracy (Contrast)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Clean) | Result date | Report paper | | --- | --- | --- | --- | | pFedFDA | 72.94 | Not recorded | 69b399f50636e5bf4afbc9a9 | | pFedGM | 72.94 | Not recorded | 69b399f50636e5bf4afbc9a9 | | FedAvgFT | 72.31 | Not recorded | 69b399f50636e5bf4afbc9a9 | | FedPAC | 72.15 | Not recorded | 69b399f50636e5bf4afbc9a9 | | pFedMe | 67.25 | Not recorded | 69b399f50636e5bf4afbc9a9 | | LG-FedAvg | 63.77 | Not recorded | 69b399f50636e5bf4afbc9a9 | | FedBAU | 61.87 | Not recorded | 69b399f50636e5bf4afbc9a9 | | FedAvg | 59.18 | Not recorded | 69b399f50636e5bf4afbc9a9 | ### pFedFDA Accuracy (Clean): 72.94. Result ID: 69b3c6dd47f34ce9249db716. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. ### pFedGM Accuracy (Clean): 72.94. Result ID: 69b3c6dd47f34ce9249db717. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. ### FedAvgFT Accuracy (Clean): 72.31. Result ID: 69b3c6dd47f34ce9249db711. [Reporting paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. ### FedPAC Accuracy (Clean): 72.15. Result ID: 69b3c6dd47f34ce9249db715. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. ### pFedMe Accuracy (Clean): 67.25. Result ID: 69b3c6dd47f34ce9249db713. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. ### LG-FedAvg Accuracy (Clean): 63.77. Result ID: 69b3c6dd47f34ce9249db714. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. ### FedBAU Accuracy (Clean): 61.87. Result ID: 69b3c6dd47f34ce9249db712. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. ### FedAvg Accuracy (Clean): 59.18. Result ID: 69b3c6dd47f34ce9249db710. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partition":"Dirichlet (0.5)","Client Type":"New Clients (Generalization)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.