Image Classification on OxfordPets Pathological Non-IID (test)
0.9882AccuracyFedOTP
Evaluation results
| Method | Links | |
|---|---|---|
| FedOTPBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 0.9882 | |
| CoOpBackbone=ResNet-50, Federated Learning Setting=Local Training, Number of Clients=102024.02 | 0.9452 | |
| pFedPromptBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 0.9184 | |
| PromptFL+FTBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 0.9123 | |
| PromptFL+FedPerBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 0.895 | |
| PromptFLBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 0.8817 | |
| PromptFL+FedProxBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 0.8725 | |
| Zero-Shot CLIPBackbone=ResNet-50, Federated Learning Setting=Local Training (Zero-shot), Number of Clients=102024.02 | 0.8447 | |
| PromptFL+FedAMPBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 0.8021 |