Open-vocabulary semantic segmentation on COCO Object
72mIoUSegEarth-OV3
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SegEarth-OV3Venue=arXiv’25, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 72 | — | |
| ActiveSAMVenue=Ours, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 72 | — | |
| SegEarth-OV32026.06 | 72 | 0.63 | |
| ActiveSAM2026.06 | 72 | 3.19 | |
| SAM 3Venue=ICLR’26, Backbone (Size)=SAM 3 (PE-L+/14), Training Strategy=Training-free2026.06 | 65.4 | — | |
| SAM^32026.06 | 65.4 | 0.24 | |
| CorrCLIPVenue=ICCV’25, Backbone (Size)=CLIP + †, Training Strategy=Training-free2026.06 | 49.4 | — | |
| ReMEVenue=ICCV’25, Backbone (Size)=CLIP + §, Training Strategy=Training-free2026.06 | 48.2 | — | |
| Talk2DINOVenue=ICCV’25, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-based2026.06 | 45.1 | — | |
| CLIPtraseVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 43.6 | — | |
| TridentVenue=ICCV’25, Backbone (Size)=CLIP + ‡, Training Strategy=Training-free2026.06 | 41.1 | — | |
| RF-CLIPVenue=AAAI’26, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 39.1 | — | |
| SFPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 37.9 | — | |
| CASSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 37.8 | — | |
| CASS2026.06 | 37.8 | 0.68 | |
| ProxyCLIPVenue=ECCV’24, Backbone (Size)=CLIP + DINOv2†(ViT-B/14), Training Strategy=Training-free2026.06 | 37.4 | — | |
| DIH-CLIPVenue=ICCV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 37.4 | — | |
| FreeDAVenue=CVPR’24, Backbone (Size)=CLIP + DINOv2 (ViT-B/14), Training Strategy=Training-free2026.06 | 36.3 | — | |
| CLIP-DINOiserVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-based2026.06 | 34.8 | — | |
| LaVGVenue=ECCV’24, Backbone (Size)=CLIP + DINO (ViT-B/8), Training Strategy=Training-free2026.06 | 34.2 | — | |
| LPOSSVenue=CVPR’25, Backbone (Size)=CLIP + DINO (ViT-B/16), Training Strategy=Training-free2026.06 | 33.4 | — | |
| NACLIPVenue=WACV’25, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 33.2 | — | |
| ClearCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 33 | — | |
| CoDeVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 32.3 | — | |
| SCLIPVenue=ECCV’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 30.5 | — | |
| TCLVenue=CVPR’23, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 30.4 | — | |
| GroupViTVenue=CVPR’22, Backbone (Size)=GroupViT (ViT-S/16), Training Strategy=Training-based2026.06 | 27.5 | — | |
| SegCLIPVenue=ICML’23, Backbone (Size)=CLIP, Training Strategy=Training-based2026.06 | 27.5 | — | |
| CaRVenue=CVPR’24, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 15.4 | — | |
| CLIPVenue=ICML’21, Backbone (Size)=CLIP, Training Strategy=Training-free2026.06 | 6.5 | — |