# Federated Image Classification on PACS Source: [Federated Image Classification on PACS]() Collection index: [llms.txt]() Data updated: 2026-04-10T00:28:16.474Z Evaluation of Federated Image Classification performance on the PACS dataset, reporting accuracy metrics across the four distinct domains (Art, Cartoon, Sketch, Photo) and aggregate statistics like Average and Delta. 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 | Federated Image Classification | | Dataset (including any stated split) | PACS | | Metric | Accuracy (Photo) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 (Photo)](): Higher is better; unit: PERCENT. - [Accuracy (Art)](): Higher is better; unit: PERCENT. - [Accuracy (Cartoon)](): Higher is better; unit: PERCENT. - [Accuracy (Sketch)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. - [Accuracy Delta](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy (Photo) | Result date | Report paper | | --- | --- | --- | --- | | FedDAP | 90.43 | Not recorded | 69d732b87d0172140ec76cec | | FedProto | 88.49 | Not recorded | 69d732b87d0172140ec76cec | | FedPLVM | 88.44 | Not recorded | 69d732b87d0172140ec76cec | | FPL | 86.72 | Not recorded | 69d732b87d0172140ec76cec | | FedRDN | 85.29 | Not recorded | 69d732b87d0172140ec76cec | | FedGA | 84.51 | Not recorded | 69d732b87d0172140ec76cec | | MOON | 83.47 | Not recorded | 69d732b87d0172140ec76cec | | COPA | 82.46 | Not recorded | 69d732b87d0172140ec76cec | | FedProx | 81.23 | Not recorded | 69d732b87d0172140ec76cec | | FedAvg | 80.89 | Not recorded | 69d732b87d0172140ec76cec | ### FedDAP Accuracy (Photo): 90.43. Result ID: 69d842e847f34ce924c052f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### FedProto Accuracy (Photo): 88.49. Result ID: 69d842e847f34ce924c052ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### FedPLVM Accuracy (Photo): 88.44. Result ID: 69d842e847f34ce924c052ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### FPL Accuracy (Photo): 86.72. Result ID: 69d842e847f34ce924c052ed. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### FedRDN Accuracy (Photo): 85.29. Result ID: 69d842e847f34ce924c052ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### FedGA Accuracy (Photo): 84.51. Result ID: 69d842e847f34ce924c052eb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### MOON Accuracy (Photo): 83.47. Result ID: 69d842e847f34ce924c052e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### COPA Accuracy (Photo): 82.46. Result ID: 69d842e847f34ce924c052ea. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### FedProx Accuracy (Photo): 81.23. Result ID: 69d842e847f34ce924c052e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. ### FedAvg Accuracy (Photo): 80.89. Result ID: 69d842e847f34ce924c052e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Communication rounds":"100","Local epochs":"10","Batch size":"16"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.