Medical Image Segmentation on Site C
82.5Dice ScoreMCDRL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MCDRLBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 82.5 | 75.1 | 94.8 | |
| MCDRLBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 80.9 | 73.6 | 94.1 | |
| BiomedCoOpBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 80.4 | 73.4 | 93.8 | |
| MCDRLBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 79.4 | 72.3 | 93.2 | |
| StyLIPBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 79.2 | 72.3 | 93.2 | |
| BiomedCoOpBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 78.8 | 71.9 | 93 | |
| StyLIPBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 77.8 | 70.8 | 92.4 | |
| BiomedCoOpBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 77.5 | 70.8 | 92.1 | |
| StyLIPBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 76.3 | 69.5 | 91.5 | |
| BaselineBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 76.1 | 69.4 | 91.6 | |
| BaselineBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 74.7 | 68.1 | 90.8 | |
| BaselineBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 73.2 | 67.1 | 89.7 |