Image Classification on Describable Textures Dataset all-to-all
49.4AccuracyCLIP-LoRA + ADK
Evaluation results
| Method | Links | |
|---|---|---|
| CLIP-LoRA + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 49.4 | |
| Rep-Adapter + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 49.3 | |
| 2SFS + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 49 | |
| 2SFSBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 45.7 | |
| Rep-AdapterBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 45.4 | |
| CLIP-LoRABackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 45.1 | |
| CLIPBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 43.6 |