Semantic Segmentation on Average across 8 datasets (val)
67.2Pixel Accuracy (pAcc)PEARL
Evaluation results
| Method | Links | |
|---|---|---|
| PEARLPub. & Year=–, Extra backbone=✗, Protocol=Training-free2026.03 | 67.2 | |
| CASSPub. & Year=CVPR’25, Extra backbone=DINOv3 (ViT-B/16), Protocol=Training-free2026.03 | 67 | |
| ProxyCLIPPub. & Year=ECCV’24, Extra backbone=DINOv2† (ViT-B/14), Protocol=Training-free2026.03 | 66.7 | |
| SFPPub. & Year=ICCV’25, Extra backbone=✗, Protocol=Training-free2026.03 | 65 | |
| NACLIPPub. & Year=WACV’25, Extra backbone=✗, Protocol=Training-free2026.03 | 64.9 | |
| CASSPub. & Year=CVPR’25, Extra backbone=DINOv2† (ViT-B/14), Protocol=Training-free2026.03 | 64.3 | |
| SCLIPPub. & Year=ECCV’24, Extra backbone=✗, Protocol=Training-free2026.03 | 63.8 | |
| LaVGPub. & Year=ECCV’24, Extra backbone=DINOv1 (ViT-B/8), Protocol=Training-free2026.03 | 63.4 | |
| CLIPtrasePub. & Year=ECCV’24, Extra backbone=✗, Protocol=Training-free2026.03 | 59.1 |