Image Classification on Flowers102 Pathological Non-IID (test)
96.23AccuracyFedOTP
Evaluation results
| Method | Links | |
|---|---|---|
| FedOTPBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 96.23 | |
| CoOpBackbone=ResNet-50, Federated Learning Setting=Local Training, Number of Clients=102024.02 | 88.23 | |
| pFedPromptBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 86.46 | |
| PromptFL+FedProxBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 74.14 | |
| PromptFLBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 73.68 | |
| PromptFL+FTBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 72.31 | |
| PromptFL+FedPerBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 72.11 | |
| PromptFL+FedAMPBackbone=ResNet-50, Federated Learning Setting=Pathological Non-IID, Number of Clients=102024.02 | 69.1 | |
| Zero-Shot CLIPBackbone=ResNet-50, Federated Learning Setting=Local Training (Zero-shot), Number of Clients=102024.02 | 62.17 |