Image Classification on Office-Home alpha=0.1 (test)
80.66Accuracy (A)FedCGS + SLOT-Align
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| FedCGS + SLOT-AlignBackbone=ViT-B/32, Pre-training=CLIP, Federated Learning Rounds=One-shot, Alignment strength (tau)=0.42026.06 | 80.66 | 75.95 | 94.89 | 88.69 | 85.05 | 7.28 | |
| FedCGSBackbone=ViT-B/32, Pre-training=CLIP, Federated Learning Rounds=One-shot2026.06 | 80.52 | 74.58 | 94.74 | 87.61 | 84.37 | 7.56 | |
| FedAvgBackbone=ViT-B/32, Pre-training=CLIP, Federated Learning Rounds=Multi-round2026.06 | 76.95 | 72.98 | 88.19 | 88.33 | 81.36 | 6.8 | |
| FedPFT + SLOT-AlignBackbone=ViT-B/32, Pre-training=CLIP, Federated Learning Rounds=One-shot, Alignment strength (tau)=0.42026.06 | 75.99 | 72.06 | 89.64 | 85.24 | 80.74 | 7.02 | |
| FedPFTBackbone=ViT-B/32, Pre-training=CLIP, Federated Learning Rounds=One-shot2026.06 | 67.99 | 61.25 | 85.51 | 82.01 | 74.19 | 9.94 | |
| O-FedAvg + SLOT-AlignBackbone=ViT-B/32, Pre-training=CLIP, Federated Learning Rounds=One-shot, Alignment strength (tau)=0.42026.06 | 67.57 | 67.51 | 78.95 | 74.16 | 72.05 | 4.81 | |
| O-FedAvgBackbone=ViT-B/32, Pre-training=CLIP, Federated Learning Rounds=One-shot2026.06 | 66.09 | 55.45 | 69.22 | 66.01 | 64.19 | 5.21 |