Image Classification on 30-Task Vision Merging Average
93.02Avg AccuracyIndividual
Evaluation Results
| Method | Links | |
|---|---|---|
| IndividualBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=12024.05 | 93.02 | |
| EMR-MERGINGBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 89.54 | |
| RegMeanBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 68.14 | |
| AdaMergingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 60.25 | |
| Task ArithmeticBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 48.89 | |
| Weight AveragingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 42.52 | |
| Ties-MergingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 37.53 |