Domain-Incremental Classification on NICO_C (test)
67.83Accuracy (T1)FedAvg
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| FedAvgBackbone=ResNet-18, Incremental Setup=Domain-Incremental2026.02 | 67.83 | 61.98 | 56.66 | 58.48 | 57.46 | 54.17 | |
| FedProxBackbone=ResNet-18, Incremental Setup=Domain-Incremental2026.02 | 67.83 | 61.83 | 55.63 | 58.48 | 54.92 | 53.66 | |
| FedEWCBackbone=ResNet-18, Incremental Setup=Domain-Incremental, lambda=0.12026.02 | 67.83 | 61.98 | 57.92 | 59.74 | 59.15 | 56.44 | |
| OSCAR-ILBackbone=ResNet-18, Incremental Setup=Domain-Incremental2026.02 | 61.78 | 58.26 | 53.72 | 54.03 | 56.16 | 53.87 | |
| OSCAR-RBackbone=ResNet-18, Incremental Setup=Domain-Incremental, lambda=0.12026.02 | 61.78 | 59.2 | 53.56 | 54.95 | 56.12 | 54.24 | |
| OSI-FLBackbone=ResNet-18, Incremental Setup=Domain-Incremental, retained samples per task=52026.02 | 61.78 | 62.5 | 58.25 | 60.72 | 62.26 | 60.19 |