Open-vocabulary semantic segmentation on Pascal VOC 2012 V20
97mIoUActiveSAM
Evaluation Results
| Method | Links | |
|---|---|---|
| ActiveSAMVenue=Ours, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 97 | |
| SegEarth-OV3Venue=arXiv’25, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 96.8 | |
| ReMEVenue=ICCV’25, Backbone (Size)=CLIP + §, Training Strategy=Training-free2026.06 | 93.2 | |
| CorrCLIPVenue=ICCV’25, Backbone (Size)=CLIP + †, Training Strategy=Training-free2026.06 | 91.5 | |
| SAM 3Venue=ICLR’26, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 88.9 | |
| Talk2DINOVenue=ICCV’25, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-based2026.06 | 88.5 | |
| CASSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 87.8 | |
| RF-CLIPVenue=AAAI’26, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 87 | |
| DIH-CLIPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 84.9 | |
| SFPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 84.5 | |
| TridentVenue=ICCV’25, Backbone (Size)=CLIP + ‡, Training Strategy=Training-free2026.06 | 84.5 | |
| FreeDAVenue=CVPR’24, Backbone (Size)=CLIP + DINOv2 (ViT-B/14), Training Strategy=Training-free2026.06 | 84.3 | |
| ProxyCLIPVenue=ECCV’24, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-free2026.06 | 83 | |
| LaVGVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 82.5 | |
| CLIPtraseVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 81 | |
| CLIP-DINOiserVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-based2026.06 | 80.9 | |
| ClearCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 80.9 | |
| SCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 80.4 | |
| GroupViTVenue=CVPR’22, Backbone (Size)=GroupViT (ViT-S/16), Training Strategy=Training-based2026.06 | 79.7 | |
| NACLIPVenue=WACV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 79.7 | |
| LPOSSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-free2026.06 | 78.8 | |
| TCLVenue=CVPR’23, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 77.5 | |
| CaRVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 73.7 | |
| CLIPVenue=ICML’21, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 49.1 |