Semantic Segmentation on COCO 20^i
72.2mIoUDiffewS
Evaluation Results
| Method | Links | |
|---|---|---|
| DiffewSShots=few-shot, Setting=In-context2024.10 | 72.2 | |
| DiffewSEncoder=Stable Diffusion, #Param=890 M, Training Protocol=Task-specific fine-tuning: Semantic + mask supervision, Shot count=52026.03 | 72.2 | |
| DiffewSShots=one-shot, Setting=In-context2024.10 | 71.3 | |
| SegGPTShots=few-shot, Setting=In-context2024.10 | 67.9 | |
| SegGPTEncoder=ViT, #Param=354 M, Training Protocol=Task-specific fine-tuning: Semantic + mask supervision, Shot count=52026.03 | 67.9 | |
| GF-SAMEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.03 | 66.8 | |
| SINEEncoder=DINOv2, #Param=373 M, Training Protocol=Task-specific fine-tuning: Semantic + mask supervision, Shot count=52026.03 | 66.1 | |
| FPTransShots=few-shot, Setting=In-context2024.10 | 65.5 | |
| INSID3Encoder=DINOv3, #Param=304 M, Training Protocol=Training free: Unsupervised pre-training, Shot count=52026.03 | 65.1 | |
| GF-SAM† + our debiasEncoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.03 | 64.6 | |
| GF-SAM†Encoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.03 | 64.4 | |
| MatcherShots=few-shot, Setting=In-context2024.10 | 60.7 | |
| MatcherEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.03 | 60.7 | |
| FPTransShots=one-shot, Setting=In-context2024.10 | 56.5 | |
| SegGPTShots=one-shot, Setting=In-context2024.10 | 56.1 | |
| MatcherShots=one-shot, Setting=In-context2024.10 | 52.7 | |
| HSNetShots=few-shot, Setting=In-context2024.10 | 50.7 | |
| VATShots=few-shot, Setting=In-context2024.10 | 49.4 | |
| VATShots=one-shot, Setting=In-context2024.10 | 42.9 | |
| HSNetShots=one-shot, Setting=In-context2024.10 | 41.7 | |
| PainterShots=one-shot, Setting=In-context2024.10 | 32.8 | |
| PainterShots=few-shot, Setting=In-context2024.10 | 32.6 | |
| PerSAM-FShots=one-shot, Setting=In-context2024.10 | 23.5 | |
| PerSAMShots=one-shot, Setting=In-context2024.10 | 23 |