Image Classification on Stanford Cars (all-to-all)
65.7AccuracyCLIP-LoRA
Evaluation results
| Method | Links | |
|---|---|---|
| CLIP-LoRABackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 65.7 | |
| CLIP-LoRA + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 65.5 | |
| 2SFSBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 65.5 | |
| CLIPBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 65.3 | |
| 2SFS + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 65.1 | |
| Rep-Adapter + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 65 | |
| Rep-AdapterBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 64 |