Image Classification on Clean ViT-B/16 (test)
93.2AccuracyRegMean++
Evaluation Results
| Method | Links | |
|---|---|---|
| RegMean++Backbone=ViT-B/16, Method Category=Training-Free Methods2025.08 | 93.2 | |
| DOGE AMBackbone=ViT-B/16, Method Category=Test-Time Adaptation2025.08 | 93.1 | |
| RegMeanBackbone=ViT-B/16, Method Category=Training-Free Methods2025.08 | 92.6 | |
| TSV-MBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 92.3 | |
| Layer-wise AdaMergingBackbone=ViT-B/16, Method Category=Test-Time Adaptation2025.08 | 90.9 | |
| Iso-CTSBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 90.7 | |
| DOGE TABackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 90.5 | |
| Iso-CBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 90.3 | |
| Task ArithmeticBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 84 | |
| Model SoupsBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 81.9 | |
| Fisher MergingBackbone=ViT-B/16, Method Category=Training-Free Methods2025.08 | 81.4 | |
| TIES-MergingBackbone=ViT-B/16, Method Category=Data-Free Methods2025.08 | 78.4 |