Semantic Segmentation on COCO 20i (test)
60.4Mean ScoreVRP-SAM
Evaluation Results
| Method | Links | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VRP-SAMVenue=This work, Image encoder=DINOv2-B, Category=based foundation methods, In-domain training=false2024.02 | 60.4 | 56.8 | 61 | 64.2 | 59.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SegGPTVenue=ICCV'23, Image encoder=Painter, Category=based foundation methods, In-domain training=false2024.02 | 56.1 | 56.3 | 57.4 | 58.9 | 51.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VRP-SAMVenue=This work, Image encoder=ResNet-50, Category=based foundation methods, In-domain training=true2024.02 | 53.9 | 48.1 | 55.8 | 60 | 51.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MatcherVenue=arXiv'23, Image encoder=DINOv2-L, Category=based foundation methods, In-domain training=false2024.02 | 52.7 | 52.7 | 53.5 | 52.6 | 52.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DCAMAVenue=ECCV'23, Image encoder=Swin-B, Category=few-shot method, In-domain training=true2024.02 | 50.9 | 49.5 | 52.7 | 52.8 | 48.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HDMNetVenue=CVPR'23, Image encoder=ResNet-50, Category=few-shot method, In-domain training=true2024.02 | 50 | 43.8 | 55.3 | 51.6 | 49.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BAM+SVFVenue=NeurIPS'22, Category=few-shot method, In-domain training=true2024.02 | 48.5 | 46.9 | 53.8 | 48.4 | 44.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VRP-SAMVenue=This work, Image encoder=VGG-16, Category=based foundation methods, In-domain training=true2024.02 | 48 | 43.6 | 51.7 | 50 | 46.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| IPMTBackbone=ResNet-101, Shot=5-shot2022.10 | 47.9 | 45.1 | 50.3 | 49.3 | 46.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FECANetBackbone=ResNet50, Shots=5-shot2023.01 | 47.6 | — | — | — | — | 44.6 | 51.5 | 48.4 | 45.8 | 71.1 | — | — | — | — | — | — | — | — | — | — | — | |
| IPMTBackbone=ResNet-50, Shot=5-shot2022.10 | 47.5 | 43.5 | 49.7 | 48.7 | 47.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FPTransVenue=NeurIPS'22, Image encoder=Deit-B/16, Category=few-shot method, In-domain training=true2024.02 | 47 | 44.4 | 48.9 | 50.6 | 44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HSNetBackbone=ResNet-50, Shot=5-shot2022.10 | 46.9 | 43.3 | 51.3 | 48.2 | 45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HSNetBackbone=ResNet50, Shots=5-shot2023.01 | 46.9 | — | — | — | — | 43.3 | 51.3 | 48.2 | 45 | 70.7 | — | — | — | — | — | — | — | — | — | — | — | |
| DCPBackbone=ResNet-50, Shot=5-shot2022.10 | 46.5 | 45.8 | 49.6 | 43.7 | 46.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CyCTRBackbone=ResNet-50, Shot=5-shot2022.10 | 45.6 | 41.1 | 48.9 | 45.2 | 47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NERTNetBackbone=ResNet-101, Shot=5-shot2022.10 | 43.2 | 42.3 | 44.4 | 44.2 | 41.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CMNBackbone=ResNet50, Shots=5-shot2023.01 | 43.1 | — | — | — | — | 42 | 50.5 | 41 | 38.9 | 63.3 | — | — | — | — | — | — | — | — | — | — | — | |
| IPMTBackbone=ResNet-50, Shot=1-shot2022.10 | 43 | 41.4 | 45.1 | 45.6 | 40 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAGNNBackbone=ResNet-101, Shot=5-shot2022.10 | 42.7 | 40.9 | 48.3 | 42.6 | 38.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| IPMTBackbone=ResNet-101, Shot=1-shot2022.10 | 42.6 | 40.5 | 45.7 | 44.8 | 39.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RePRIBackbone=ResNet-50, Shot=5-shot2022.10 | 42.1 | 38.5 | 46.2 | 40 | 43.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CWTBackbone=ResNet-101, Shot=5-shot2022.10 | 42 | 38.5 | 46.7 | 39.4 | 43.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FECANetBackbone=ResNet50, Shots=1-shot2023.01 | 41.6 | — | — | — | — | 38.5 | 44.6 | 42.6 | 40.7 | 69.6 | — | — | — | — | — | — | — | — | — | — | — | |
| REPRIBackbone=ResNet50, Shots=5-shot2023.01 | 41.6 | — | — | — | — | 39.3 | 45.4 | 39.7 | 41.8 | — | — | — | — | — | — | — | — | — | — | — | — | |
| FECANetBackbone=VGG16, Shots=5-shot2023.01 | 41.5 | — | — | — | — | 39.7 | 43.6 | 42.9 | 39.7 | 67.7 | — | — | — | — | — | — | — | — | — | — | — | |
| DCPBackbone=ResNet-50, Shot=1-shot2022.10 | 41.4 | 40.9 | 43.8 | 42.6 | 38.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CWTBackbone=ResNet-50, Shot=5-shot2022.10 | 41.3 | 40.1 | 43.8 | 39 | 42.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CWTBackbone=ResNet50, Shots=5-shot2023.01 | 41.3 | — | — | — | — | 40.1 | 43.8 | 39 | 42.4 | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATVenue=ECCV'23, Image encoder=ResNet-50, Category=few-shot method, In-domain training=true2024.02 | 41.3 | 39 | 43.8 | 42.6 | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CyCTRBackbone=ResNet-50, Shot=1-shot2022.10 | 40.3 | 38.9 | 43 | 39.6 | 39.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NERTNetBackbone=ResNet-50, Shot=5-shot2022.10 | 40.3 | 38.2 | 44.1 | 40.4 | 38.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NTRENetBackbone=ResNet50, Shots=5-shot2023.01 | 40.3 | — | — | — | — | 38.2 | 44.1 | 40.4 | 38.4 | 69.2 | — | — | — | — | — | — | — | — | — | — | — | |
| SCLBackbone=ResNet-101, Shot=5-shot2022.10 | 39.9 | 38.9 | 40.5 | 41.5 | 38.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NERTNetBackbone=ResNet-50, Shot=1-shot2022.10 | 39.3 | 36.8 | 42.6 | 39.9 | 37.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CMNBackbone=ResNet50, Shots=1-shot2023.01 | 39.3 | — | — | — | — | 37.9 | 44.8 | 38.7 | 35.6 | 61.7 | — | — | — | — | — | — | — | — | — | — | — | |
| NTRENetBackbone=ResNet50, Shots=1-shot2023.01 | 39.3 | — | — | — | — | 36.8 | 42.6 | 39.9 | 37.9 | 68.5 | — | — | — | — | — | — | — | — | — | — | — | |
| HSNetBackbone=ResNet-50, Shot=1-shot2022.10 | 39.2 | 36.3 | 43.1 | 38.7 | 38.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HSNetBackbone=ResNet50, Shots=1-shot2023.01 | 39.2 | — | — | — | — | 36.3 | 43.1 | 38.7 | 38.7 | 68.2 | — | — | — | — | — | — | — | — | — | — | — | |
| NERTNetBackbone=ResNet-101, Shot=1-shot2022.10 | 39.1 | 38.3 | 40.4 | 39.5 | 38.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PFENetBackbone=ResNet50, Shots=5-shot2023.01 | 39 | — | — | — | — | 36.5 | 43.3 | 37.8 | 38.4 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PPNetBackbone=ResNet50, Shots=5-shot2023.01 | 38.5 | — | — | — | — | 39 | 40.8 | 37.1 | 37.3 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PFENetBackbone=ResNet-101, Shot=5-shot2022.10 | 37.4 | 38.5 | 38.6 | 38.2 | 34.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAGNNBackbone=ResNet-101, Shot=1-shot2022.10 | 37.2 | 36.1 | 41 | 38.2 | 33.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SCLBackbone=ResNet-101, Shot=1-shot2022.10 | 37 | 36.4 | 38.6 | 37.5 | 35.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ASRBackbone=ResNet50, Shots=5-shot2023.01 | 36.7 | — | — | — | — | 33.1 | 39.5 | 34.1 | 36.2 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PFENetBackbone=ResNet50, Shots=1-shot2023.01 | 35.8 | — | — | — | — | 36.5 | 38.6 | 34.5 | 33.8 | — | — | — | — | — | — | — | — | — | — | — | — | |
| RPMMBackbone=ResNet-50, Shot=5-shot2022.10 | 35.5 | 33.8 | 42 | 33 | 33.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RPMMBackbone=ResNet50, Shots=5-shot2023.01 | 35.5 | — | — | — | — | 33.8 | 42 | 33 | 33.3 | — | — | — | — | — | — | — | — | — | — | — | — | |
| FECANetBackbone=VGG16, Shots=1-shot2023.01 | 35.4 | — | — | — | — | 34.1 | 37.5 | 35.8 | 34.1 | 65.5 | — | — | — | — | — | — | — | — | — | — | — | |
| PMMBackbone=ResNet50, Shots=5-shot2023.01 | 34.3 | — | — | — | — | 33 | 40.6 | 30.3 | 33.3 | — | — | — | — | — | — | — | — | — | — | — | — | |
| REPRIBackbone=ResNet50, Shots=1-shot2023.01 | 34.1 | — | — | — | — | 32 | 38.7 | 32.7 | 33.1 | — | — | — | — | — | — | — | — | — | — | — | — | |
| RePRIBackbone=ResNet-50, Shot=1-shot2022.10 | 34 | 31.2 | 38.1 | 33.3 | 33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ASRBackbone=ResNet50, Shots=1-shot2023.01 | 33.8 | — | — | — | — | 30.6 | 36.7 | 32.6 | 35.3 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PainterVenue=CVPR'23, Image encoder=Painter, Category=based foundation methods, In-domain training=false2024.02 | 33.1 | 31.2 | 35.3 | 33.5 | 32.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CWTBackbone=ResNet-50, Shot=1-shot2022.10 | 32.9 | 32.2 | 36 | 31.6 | 31.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CWTBackbone=ResNet50, Shots=1-shot2023.01 | 32.9 | — | — | — | — | 32.2 | 36 | 31.6 | 31.6 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PRNetBackbone=VGG16, Shots=5-shot2023.01 | 32.8 | — | — | — | — | 31.1 | 36.5 | 31.5 | 32 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PFENetBackbone=ResNet-101, Shot=1-shot2022.10 | 32.4 | 34.3 | 33 | 32.3 | 30.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CWTBackbone=ResNet-101, Shot=1-shot2022.10 | 32.4 | 30.3 | 36.6 | 30.5 | 32.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RPMMBackbone=ResNet-50, Shot=1-shot2022.10 | 30.6 | 29.5 | 36.8 | 29 | 27 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RPMMBackbone=ResNet50, Shots=1-shot2023.01 | 30.6 | — | — | — | — | 29.5 | 36.8 | 28.9 | 27 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PMMBackbone=ResNet50, Shots=1-shot2023.01 | 29.6 | — | — | — | — | 29.3 | 34.8 | 27.1 | 27.3 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PRNetBackbone=VGG16, Shots=1-shot2023.01 | 29 | — | — | — | — | 27.5 | 33 | 26.7 | 29 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PPNetBackbone=ResNet50, Shots=1-shot2023.01 | 29 | — | — | — | — | 28.1 | 30.8 | 29.5 | 27.7 | — | — | — | — | — | — | — | — | — | — | — | — | |
| FWBBackbone=ResNet50, Shots=5-shot2023.01 | 23.6 | — | — | — | — | 19.1 | 21.4 | 23.9 | 30 | — | — | — | — | — | — | — | — | — | — | — | — | |
| PerSAMVenue=arXiv'23, Category=based foundation methods, In-domain training=false2024.02 | 23 | 23.1 | 23.6 | 22 | 23.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FWBBackbone=VGG16, Shots=5-shot2023.01 | 22.6 | — | — | — | — | 20.9 | 19.2 | 21.9 | 28.4 | — | — | — | — | — | — | — | — | — | — | — | — | |
| FWBBackbone=ResNet50, Shots=1-shot2023.01 | 21.1 | — | — | — | — | 16.9 | 17.9 | 20.9 | 28.8 | — | — | — | — | — | — | — | — | — | — | — | — | |
| FWBBackbone=VGG16, Shots=1-shot2023.01 | 20 | — | — | — | — | 18.4 | 16.7 | 19.6 | 25.4 | — | — | — | — | — | — | — | — | — | — | — | — | |
| A-MCGBackbone=ResNet-50, Shot=1-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 59.2 | — | |
| A-MCGBackbone=ResNet-50, Shot=5-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 63.5 | — | |
| AENetSetting=5-shot2026.07 | — | — | — | — | — | — | — | — | — | 78.5 | — | — | — | — | — | — | — | — | — | — | — | |
| AENetSetting=1-shot2026.07 | — | — | — | — | — | — | — | — | — | 74.4 | — | — | — | — | — | — | — | — | — | — | — | |
| APANetBackbone=VGG-16, Shot=1-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 35.6 | 40 | 36 | 37.1 | 37.2 | 50.5 | 64.6 | 64.7 | 66.4 | 61.6 | — | |
| APANetBackbone=VGG-16, Shot=5-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 40.1 | 48.7 | 43.3 | 40.7 | 43.2 | 54.1 | 70.5 | 69.2 | 70 | 66 | — | |
| APANetBackbone=ResNet-50, Shot=1-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 37.5 | 43.9 | 39.7 | 40.7 | 40.5 | 50.1 | 67.9 | 67.8 | 68.6 | 63.6 | — | |
| APANetBackbone=ResNet-50, Shot=5-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 39.8 | 46.9 | 43.1 | 42.2 | 43 | 56.7 | 69.7 | 70.2 | 70.1 | 66.7 | — | |
| APANetBackbone=ResNet-101, Shot=1-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 40.7 | 44.6 | 42.5 | 39.6 | 41.9 | 54 | 67.9 | 68.9 | 68.3 | 64.8 | — | |
| APANetBackbone=ResNet-101, Shot=5-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 45.7 | 49.7 | 47.4 | 42.8 | 46.4 | 63.6 | 71.4 | 72.2 | 72 | 69.8 | — | |
| ASGNetShot=12023.05 | — | — | — | — | — | — | — | — | — | 60.4 | — | — | — | — | — | — | — | — | — | — | — | |
| ASGNetShot=52023.05 | — | — | — | — | — | — | — | — | — | 67 | — | — | — | — | — | — | — | — | — | — | 6.6 | |
| CLIPixSetting=0-shot2026.07 | — | — | — | — | — | — | — | — | — | 78.8 | — | — | — | — | — | — | — | — | — | — | — | |
| DACMSetting=5-shot2026.07 | — | — | — | — | — | — | — | — | — | 71.6 | — | — | — | — | — | — | — | — | — | — | — | |
| DACMSetting=1-shot2026.07 | — | — | — | — | — | — | — | — | — | 68.9 | — | — | — | — | — | — | — | — | — | — | — | |
| DANShot=12023.05 | — | — | — | — | — | — | — | — | — | 62.3 | — | — | — | — | — | — | — | — | — | — | — | |
| DANShot=52023.05 | — | — | — | — | — | — | — | — | — | 63.9 | — | — | — | — | — | — | — | — | — | — | 1.6 | |
| FWBBackbone=VGG-16, Shot=1-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 18.4 | 16.7 | 19.6 | 25.4 | 20 | — | — | — | — | — | — | |
| FWBBackbone=VGG-16, Shot=5-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 20.9 | 19.2 | 21.9 | 28.4 | 22.6 | — | — | — | — | — | — | |
| FWBBackbone=ResNet-101, Shot=1-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 19.9 | 18 | 21 | 28.9 | 21.2 | — | — | — | — | — | — | |
| FWBBackbone=ResNet-101, Shot=5-Shot2021.11 | — | — | — | — | — | — | — | — | — | — | 19.1 | 21.5 | 23.9 | 30.1 | 23.7 | — | — | — | — | — | — | |
| HDMNetSetting=5-shot2026.07 | — | — | — | — | — | — | — | — | — | 77.7 | — | — | — | — | — | — | — | — | — | — | — | |
| HDMNetSetting=1-shot2026.07 | — | — | — | — | — | — | — | — | — | 72.2 | — | — | — | — | — | — | — | — | — | — | — | |
| HMNetSetting=5-shot2026.07 | — | — | — | — | — | — | — | — | — | 77.6 | — | — | — | — | — | — | — | — | — | — | — | |
| HMNetSetting=1-shot2026.07 | — | — | — | — | — | — | — | — | — | 74.5 | — | — | — | — | — | — | — | — | — | — | — | |
| HSNetShot=12023.05 | — | — | — | — | — | — | — | — | — | 68.2 | — | — | — | — | — | — | — | — | — | — | — | |
| HSNetShot=52023.05 | — | — | — | — | — | — | — | — | — | 70.7 | — | — | — | — | — | — | — | — | — | — | 2.5 | |
| HSNetSetting=5-shot2026.07 | — | — | — | — | — | — | — | — | — | 72.4 | — | — | — | — | — | — | — | — | — | — | — | |
| HSNetSetting=1-shot2026.07 | — | — | — | — | — | — | — | — | — | 69.1 | — | — | — | — | — | — | — | — | — | — | — | |
| LSegSetting=0-shot2026.07 | — | — | — | — | — | — | — | — | — | 59.9 | — | — | — | — | — | — | — | — | — | — | — |