Organ-level semantic segmentation on Pear Flower
73.03mIoUSPROUT
Evaluation results
| Method | Links | |
|---|---|---|
| SPROUTPre-training Dataset=MCD-2.6M, Model Architecture=UDiT-L2026.03 | 73.03 | |
| SPROUTPre-training Dataset=MCD-2.6M, Model Architecture=UDiT-B2026.03 | 71.01 | |
| DINOv2Pre-training Dataset=LVD-142M, Model Architecture=ViT-B-162026.03 | 63.23 | |
| DINOv2Pre-training Dataset=LVD-142M, Model Architecture=ViT-S-162026.03 | 63.12 | |
| CLIPPre-training Dataset=WIT-4M, Model Architecture=ViT-L-142026.03 | 62.4 | |
| DINOv3Pre-training Dataset=LVD-1689M, Model Architecture=ViT-L-162026.03 | 61.86 | |
| DINOv2Pre-training Dataset=LVD-142M, Model Architecture=ViT-L-162026.03 | 61.7 | |
| DINOv3Pre-training Dataset=LVD-1689M, Model Architecture=ViT-B-162026.03 | 61.11 | |
| SigLIPPre-training Dataset=WebLI-10B, Model Architecture=ViT-L-162026.03 | 60.71 | |
| SigLIPPre-training Dataset=WebLI-10B, Model Architecture=ViT-B-162026.03 | 59.93 | |
| CLIPPre-training Dataset=WIT-4M, Model Architecture=ViT-B-162026.03 | 59.72 | |
| MSNPre-training Dataset=ImageNet-1K, Model Architecture=ViT-B-162026.03 | 59.57 | |
| MSNPre-training Dataset=ImageNet-1K, Model Architecture=ViT-S-162026.03 | 59.47 | |
| DINOv3Pre-training Dataset=LVD-1689M, Model Architecture=ViT-S-162026.03 | 59.43 | |
| MSNPre-training Dataset=ImageNet-1K, Model Architecture=ViT-L-162026.03 | 59.04 | |
| SPROUTPre-training Dataset=MCD-2.6M, Model Architecture=UDiT-S2026.03 | 51.19 | |
| MAEPre-training Dataset=ImageNet-1K, Model Architecture=ViT-L-162026.03 | 11.85 | |
| MAEPre-training Dataset=ImageNet-1K, Model Architecture=ViT-B-162026.03 | 8.69 |