Semantic-level object discovery on VOC
69.8mIoUToCo
Evaluation Results
| Method | Links | |
|---|---|---|
| ToCoDownstream tasks=sOD, Input=I + L2024.07 | 69.8 | |
| GLASS-SemDownstream tasks=iOD + PP + CG + CPG, Input=I, Pre-trained models=SD + DINOv2 + BLIP-22024.07 | 68.9 | |
| OVDiffDownstream tasks=sOD, Input=I + C, Pre-trained models=SD + DINO + CLIP2024.07 | 66.3 | |
| AFADownstream tasks=sOD, Input=I + L2024.07 | 66 | |
| DiffCutDownstream tasks=sOD, Input=I, Pre-trained models=SD2024.07 | 65.2 | |
| Dataset DiffusionDownstream tasks=sOD, Input=I, Pre-trained models=SD + BLIP-22024.07 | 64.8 | |
| 1StageDownstream tasks=sOD, Input=I + L2024.07 | 62.7 | |
| DiffuMaskDownstream tasks=sOD, Input=I + C, Pre-trained models=SD + CLIP + [1]2024.07 | 57.4 | |
| SPOTDownstream tasks=iOD + PP, Input=I, Pre-trained models=DINO2024.07 | 55.3 | |
| OVSegDownstream tasks=sOD, Input=I + C, Pre-trained models=CLIP2024.07 | 53.8 | |
| SegCLIPDownstream tasks=sOD, Input=I + C, Pre-trained models=CLIP2024.07 | 52.6 | |
| CLIPPYDownstream tasks=sOD, Input=I + C, Pre-trained models=CLIP2024.07 | 52.2 | |
| COMUSDownstream tasks=sOD, Input=I, Pre-trained models=DINO2024.07 | 50 | |
| DINOSAUR-TransformerDownstream tasks=iOD + PP, Input=I, Pre-trained models=DINO2024.07 | 47.5 | |
| DINOSAUR-MLPDownstream tasks=iOD + PP, Input=I, Pre-trained models=DINO2024.07 | 41 | |
| EmerDiffDownstream tasks=sOD, Input=I, Pre-trained models=SD2024.07 | 40.3 | |
| MaskCLIPDownstream tasks=sOD, Input=I + C, Pre-trained models=CLIP2024.07 | 38.8 | |
| DeepSpectralDownstream tasks=sOD, Input=I, Pre-trained models=DINO2024.07 | 37.2 | |
| StableLSDDownstream tasks=iOD + PP + CG, Input=I, Pre-trained models=SD + DINOv22024.07 | 35.4 |