Part Segmentation on PASCAL-PART
50.5mIoUINSID3
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| INSID3Encoder=DINOv3, #Param=304 M, Training Protocol=Training free, Supervision Type=Unsupervised pre-training2026.03 | 50.5 | — | — | — | — | |
| GF-SAM† + debiasEncoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training, Debias=True2026.03 | 46.2 | — | — | — | — | |
| GF-SAM†Encoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.03 | 44.9 | — | — | — | — | |
| GF-SAMModel Category=generalist model, Shots=1-shot2024.10 | 44.5 | — | — | — | — | |
| GF-SAMEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.03 | 44.5 | — | — | — | — | |
| MatcherModel Category=generalist model, Shots=1-shot2024.10 | 42.9 | — | — | — | — | |
| MatcherEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.03 | 42.9 | — | — | — | — | |
| SegICEncoder=DINOv2, #Param=310 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.03 | 39.9 | — | — | — | — | |
| SegIC (COCO)Encoder=DINOv2, #Param=310 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision, dataset split=COCO2026.03 | 38.6 | — | — | — | — | |
| VRP-SAMBackbone=DINOv2-B2024.02 | 36.2 | 30.3 | 52.1 | 25.8 | 36.7 | |
| SINEEncoder=DINOv2, #Param=373 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.03 | 36.2 | — | — | — | — | |
| SegGPT2024.02 | 35.8 | 22.8 | 50.9 | 31.3 | 38 | |
| SegGPTEncoder=ViT, #Param=354 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.03 | 35.8 | — | — | — | — | |
| VRP-SAMBackbone=RN502024.02 | 35.4 | 23.4 | 56.6 | 25.8 | 35.6 | |
| DiffewSEncoder=Stable Diffusion, #Param=890 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.03 | 34 | — | — | — | — | |
| PerSAM-FModel Category=generalist model, Shots=1-shot2024.10 | 32.9 | — | — | — | — | |
| PerSAMModel Category=generalist model, Shots=1-shot2024.10 | 32.5 | — | — | — | — | |
| PerSAMEncoder=SAM, #Param=640 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.03 | 32.5 | — | — | — | — | |
| HSNetModel Category=specialist model, Shots=1-shot2024.10 | 32.4 | — | — | — | — | |
| Painter2024.02 | 30.4 | 20.2 | 49.5 | 17.6 | 34.4 | |
| PainterEncoder=ViT, #Param=354 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.03 | 30.4 | — | — | — | — | |
| PerSAM2024.02 | 30.1 | 19.9 | 51.8 | 18.6 | 32 |