Organ-level semantic segmentation on Rice
87.11Green Veg IoUSPROUT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SPROUTPre-training Dataset=MCD-2.6M, Model Architecture=UDiT-L2026.03 | 87.11 | 55.29 | 81.15 | |
| SPROUTPre-training Dataset=MCD-2.6M, Model Architecture=UDiT-B2026.03 | 86.82 | 53.12 | 80.06 | |
| SPROUTPre-training Dataset=MCD-2.6M, Model Architecture=UDiT-S2026.03 | 86.8 | 51.18 | 78.6 | |
| CLIPPre-training Dataset=WIT-4M, Model Architecture=ViT-L-142026.03 | 82.01 | 50.06 | 74.77 | |
| DINOv2Pre-training Dataset=LVD-142M, Model Architecture=ViT-L-162026.03 | 81.19 | 48.74 | 75.04 | |
| DINOv2Pre-training Dataset=LVD-142M, Model Architecture=ViT-B-162026.03 | 80.74 | 47.77 | 73.67 | |
| DINOv2Pre-training Dataset=LVD-142M, Model Architecture=ViT-S-162026.03 | 80.71 | 47.54 | 72.77 | |
| DINOv3Pre-training Dataset=LVD-1689M, Model Architecture=ViT-L-162026.03 | 79.96 | 47.52 | 73.87 | |
| SigLIPPre-training Dataset=WebLI-10B, Model Architecture=ViT-L-162026.03 | 79.48 | 45.74 | 71.92 | |
| CLIPPre-training Dataset=WIT-4M, Model Architecture=ViT-B-162026.03 | 79.4 | 44.96 | 70.05 | |
| MSNPre-training Dataset=ImageNet-1K, Model Architecture=ViT-S-162026.03 | 79.39 | 45.53 | 71.07 | |
| DINOv3Pre-training Dataset=LVD-1689M, Model Architecture=ViT-B-162026.03 | 79.38 | 46.75 | 72.92 | |
| MSNPre-training Dataset=ImageNet-1K, Model Architecture=ViT-B-162026.03 | 79.25 | 46.06 | 71.1 | |
| SigLIPPre-training Dataset=WebLI-10B, Model Architecture=ViT-B-162026.03 | 78.99 | 45.51 | 71.31 | |
| DINOv3Pre-training Dataset=LVD-1689M, Model Architecture=ViT-S-162026.03 | 78.88 | 46.84 | 71.73 | |
| MSNPre-training Dataset=ImageNet-1K, Model Architecture=ViT-L-162026.03 | 78.78 | 43.78 | 69.7 | |
| MAEPre-training Dataset=ImageNet-1K, Model Architecture=ViT-B-162026.03 | 44.86 | 17.86 | 20.06 | |
| MAEPre-training Dataset=ImageNet-1K, Model Architecture=ViT-L-162026.03 | 44.82 | 17.54 | 24.43 |