Open-vocabulary semantic segmentation on Pascal Context 59 (P59)
60.1mIoUActiveSAM
Evaluation Results
| Method | Links | |
|---|---|---|
| ActiveSAMVenue=Ours, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 60.1 | |
| SegEarth-OV3Venue=arXiv’25, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 59.2 | |
| ReMEVenue=ICCV’25, Backbone (Size)=CLIP + §, Training Strategy=Training-free2026.06 | 53.1 | |
| CorrCLIPVenue=ICCV’25, Backbone (Size)=CLIP + †, Training Strategy=Training-free2026.06 | 50.8 | |
| SAM 3Venue=ICLR’26, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 50 | |
| Talk2DINOVenue=ICCV’25, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-based2026.06 | 42.4 | |
| TridentVenue=ICCV’25, Backbone (Size)=CLIP + ‡, Training Strategy=Training-free2026.06 | 42.2 | |
| RF-CLIPVenue=AAAI’26, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 41.4 | |
| CASSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 40.2 | |
| SFPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 39.9 | |
| FreeDAVenue=CVPR’24, Backbone (Size)=CLIP + DINOv2 (ViT-B/14), Training Strategy=Training-free2026.06 | 39.7 | |
| DIH-CLIPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 39.7 | |
| LPOSSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-free2026.06 | 37.8 | |
| ProxyCLIPVenue=ECCV’24, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-free2026.06 | 37.2 | |
| CLIP-DINOiserVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-based2026.06 | 35.9 | |
| ClearCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 35.9 | |
| NACLIPVenue=WACV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 35.2 | |
| LaVGVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 34.7 | |
| SCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 34.1 | |
| CLIPtraseVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 33.8 | |
| GEMVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 32.6 | |
| TCLVenue=CVPR’23, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 30.3 | |
| GroupViTVenue=CVPR’22, Backbone (Size)=GroupViT (ViT-S/16), Training Strategy=Training-based2026.06 | 23.4 | |
| CaRVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 18.4 | |
| CLIPVenue=ICML’21, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 11.2 |