Image Classification on CIFAR-100 10-shot (test)
87.39Top-1 AccEVA
Evaluation Results
| Method | Links | |
|---|---|---|
| EVAModel=BEIT-L/14, Pre-training Dataset=CLIP OpenAI, IN-22K, IN-1K, Evaluation Protocol=Linear Probing2024.11 | 87.39 | |
| SABackbone=ViT-Large, Shot-count=10-shot2025.03 | 85.45 | |
| Split LearningBackbone=ViT-Large, Shot-count=10-shot2025.03 | 83.66 | |
| Linear ProbingBackbone=ViT-Large, Shot-count=10-shot2025.03 | 83.28 | |
| Fine TuningBackbone=Swin-L2025.03 | 82.65 | |
| Fine TuningBackbone=ViT-Large, Shot-count=10-shot2025.03 | 81.82 | |
| SABackbone=Swin-L2025.03 | 80.96 | |
| Offsite TuningBackbone=Swin-L2025.03 | 80.68 | |
| Offsite TuningBackbone=ViT-Large, Shot-count=10-shot2025.03 | 80.11 | |
| Linear ProbingBackbone=Swin-L2025.03 | 79.83 | |
| ScaleKDModel=ViT-B/16, Pre-training Dataset=IN-1K, Evaluation Protocol=Linear Probing2024.11 | 77.52 | |
| CLIPModel=ViT-B/16, Pre-training Dataset=CLIP OpenAI, IN-12K, IN-1K, Evaluation Protocol=Linear Probing2024.11 | 77.37 | |
| CLIPModel=ViT-B/16, Pre-training Dataset=LAION-300M, Evaluation Protocol=Linear Probing2024.11 | 77.21 | |
| CLIPModel=ViT-B/16, Pre-training Dataset=LAION-2B, IN-12K, IN-1K, Evaluation Protocol=Linear Probing2024.11 | 76.77 | |
| Split LearningBackbone=Swin-L2025.03 | 73.59 | |
| CLIPModel=ViT-B/16, Pre-training Dataset=LAION-2B, IN-1K, Evaluation Protocol=Linear Probing2024.11 | 72.34 | |
| From-scratchModel=ViT-B/16, Pre-training Dataset=IN-1K, Evaluation Protocol=Linear Probing2024.11 | 66.77 | |
| LN-TUNEBackbone=ViT-Large, Shot-count=10-shot2025.03 | 47.97 | |
| LN-TUNEBackbone=Swin-L2025.03 | 27.42 |