Image Classification on Caltech-101 all-to-all
94AccuracyRep-Adapter + ADK
Evaluation results
| Method | Links | |
|---|---|---|
| Rep-Adapter + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 94 | |
| Rep-AdapterBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 93.9 | |
| 2SFS + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 93.9 | |
| CLIP-LoRA + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 93.6 | |
| 2SFSBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 93.6 | |
| CLIP-LoRABackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 93.2 | |
| CLIPBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 92.9 |