Open-vocabulary semantic segmentation on Pascal VOC 2012 V21
83.8mIoUActiveSAM
Evaluation Results
| Method | Links | |
|---|---|---|
| ActiveSAMVenue=Ours, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 83.8 | |
| ReMEVenue=ICCV’25, Backbone (Size)=CLIP + §, Training Strategy=Training-free2026.06 | 82.2 | |
| SAM 3Venue=ICLR’26, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 81.9 | |
| SegEarth-OV3Venue=arXiv’25, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 79.8 | |
| CorrCLIPVenue=ICCV’25, Backbone (Size)=CLIP + †, Training Strategy=Training-free2026.06 | 76.7 | |
| RF-CLIPVenue=AAAI’26, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 67.2 | |
| TridentVenue=ICCV’25, Backbone (Size)=CLIP + ‡, Training Strategy=Training-free2026.06 | 67.1 | |
| Talk2DINOVenue=ICCV’25, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-based2026.06 | 65.8 | |
| CASSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 65.8 | |
| DIH-CLIPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 64.2 | |
| SFPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 63.9 | |
| CLIP-DINOiserVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-based2026.06 | 62.1 | |
| LaVGVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 62.1 | |
| LPOSSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-free2026.06 | 61.1 | |
| SAM-CLIPVenue=CVPR’24, Backbone (Size)=CLIP + SAM (ViT-B/16), Training Strategy=Training-based2026.06 | 60.6 | |
| SCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 59.1 | |
| NACLIPVenue=WACV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 58.9 | |
| ProxyCLIPVenue=ECCV’24, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-free2026.06 | 58.6 | |
| CoDeVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 57.7 | |
| SegCLIPVenue=ICML’23, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 52.6 | |
| FreeDAVenue=CVPR’24, Backbone (Size)=CLIP + DINOv2 (ViT-B/14), Training Strategy=Training-free2026.06 | 51.8 | |
| ClearCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 51.8 | |
| TCLVenue=CVPR’23, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 51.2 | |
| CLIPtraseVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 50.9 | |
| GroupViTVenue=CVPR’22, Backbone (Size)=GroupViT (ViT-S/16), Training Strategy=Training-based2026.06 | 50.4 | |
| CaRVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 48.6 | |
| GEMVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 46.2 | |
| CLIPVenue=ICML’21, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 18.6 |