Image Classification on Oxford-IIIT Pets all-to-all
92AccuracyCLIP-LoRA + ADK
Evaluation results
| Method | Links | |
|---|---|---|
| CLIP-LoRA + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 92 | |
| 2SFS + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 91.7 | |
| Rep-Adapter + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 90.9 | |
| 2SFSBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 90.2 | |
| Rep-AdapterBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 89.9 | |
| CLIP-LoRABackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 89.9 | |
| CLIPBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 89.1 |