Multi-task Image Classification on 50 computer vision tasks
90.8AccuracyFine-tuned
Evaluation results
| Method | Links | |
|---|---|---|
| Fine-tunedBackbone=ViT-B/32, Category=Task-specific baseline2026.06 | 90.8 | |
| TSV-C + SiMBackbone=ViT-B/32, Merging Type=Dynamic model merging, Base Framework=TSV-C2026.06 | 80.2 | |
| EMR + SiMBackbone=ViT-B/32, Merging Type=Dynamic model merging, Base Framework=EMR2026.06 | 76.7 | |
| TM-TA + SiMBackbone=ViT-B/32, Merging Type=Dynamic model merging, Base Framework=TM-TA2026.06 | 73.1 | |
| TM-TIES + SiMBackbone=ViT-B/32, Merging Type=Dynamic model merging, Base Framework=TM-TIES2026.06 | 72.2 | |
| TSV-MBackbone=ViT-B/32, Merging Type=Static model merging2026.06 | 66.6 | |
| WEMoEBackbone=ViT-B/32, Merging Type=Dynamic model merging2026.06 | 51.6 | |
| Iso-CBackbone=ViT-B/32, Merging Type=Static model merging2026.06 | 49.1 | |
| TIES-MergingBackbone=ViT-B/32, Merging Type=Static model merging2026.06 | 47.5 | |
| Task ArithmeticBackbone=ViT-B/32, Merging Type=Static model merging2026.06 | 46.8 | |
| TWIN-MergingBackbone=ViT-B/32, Merging Type=Dynamic model merging2026.06 | 36.4 | |
| DaWinBackbone=ViT-B/32, Merging Type=Dynamic model merging2026.06 | 33.1 | |
| MoW-MergingBackbone=ViT-B/32, Merging Type=Dynamic model merging2026.06 | 30.1 |