Medical Image Segmentation on Site D
79.6Dice ScoreMCDRL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MCDRLBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 79.6 | 72.4 | 93.1 | |
| MCDRLBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 77.9 | 70.9 | 92.3 | |
| BiomedCoOpBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 77.5 | 70.5 | 92 | |
| MCDRLBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 76.4 | 69.5 | 91.4 | |
| BiomedCoOpBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 76.1 | 69.3 | 91.1 | |
| StyLIPBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 76.1 | 69.3 | 91.3 | |
| BiomedCoOpBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 74.8 | 68.4 | 90.1 | |
| StyLIPBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 74.5 | 67.9 | 90.2 | |
| StyLIPBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 73.2 | 66.8 | 89.3 | |
| BaselineBackbone=ViT-L/14, Pre-trained weights=CLIP2025.08 | 72.8 | 66.2 | 89.5 | |
| BaselineBackbone=ViT-B/16, Pre-trained weights=CLIP2025.08 | 71.2 | 64.9 | 88.4 | |
| BaselineBackbone=ResNet-50, Pre-trained weights=CLIP2025.08 | 69.5 | 63.1 | 87.2 |