Image Classification on EuroSAT (all-to-all)
47.5AccuracyCLIP
Evaluation results
| Method | Links | |
|---|---|---|
| CLIPBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 47.5 | |
| Rep-Adapter + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 47.5 | |
| 2SFS + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 47.5 | |
| CLIP-LoRA + ADKBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 44.4 | |
| 2SFSBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 37.9 | |
| Rep-AdapterBackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 37.6 | |
| CLIP-LoRABackbone=ViT-B/16, Training Dataset=ImageNet, Evaluation Protocol=all-to-all2025.12 | 34.5 |