Model Merging on Large-scale tasks 16 tasks merged
91.5Average Normalized AccuracyDOGE AM
Evaluation Results
| Method | Links | |
|---|---|---|
| DOGE AMBackbone=ViT-B/16, Method Category=Test-Time Adaption Methods2025.08 | 91.5 | |
| RegMean++Backbone=ViT-B/16, Method Category=Training-Free Methods2025.08 | 89.6 | |
| RegMeanBackbone=ViT-B/16, Method Category=Training-Free Methods2025.08 | 88.9 | |
| Layer-wise AdaMergingBackbone=ViT-B/16, Method Category=Test-Time Adaption Methods2025.08 | 88.8 | |
| TSV-MBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 88.7 | |
| Iso-CTSBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 88.6 | |
| Iso-CBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 84.8 | |
| DOGE TABackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 82.1 | |
| Fisher MergingBackbone=ViT-B/16, Method Category=Training-Free Methods2025.08 | 80.3 | |
| Model SoupsBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 78 | |
| TIES-MergingBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 76.6 | |
| Task ArithmeticBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 60.5 |