Open Vocabulary Semantic Segmentation on PASCAL Context 59
60.1mIoUActiveSAM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ActiveSAM2026.06 | 60.1 | 4.1 | |
| SegEarth-OV32026.06 | 59.2 | 0.86 | |
| SAM^32026.06 | 50 | 0.32 | |
| CASS2026.06 | 40.2 | 0.81 | |
| INSIGHT_thresParadigm=Use Frozen CLIP with Interpretability, Background Prompt=No2026.01 | 36.5 | — | |
| CLIP-DINOiserParadigm=Use Frozen CLIP, Background Prompt=No, Protocol=Rerun (*)2026.01 | 36 | — | |
| SigLIPv2 + UniRefinerViT=So/16, Background category=Without background category, Protocol=Zero-shot2026.05 | 34.3 | — | |
| OVDiffParadigm=Build prototypes per class, Extra Backbones=DINO & SD, Background Prompt=No2026.01 | 33.7 | — | |
| INSIGHTParadigm=Use Frozen CLIP with Interpretability, Background Prompt=No2026.01 | 32.9 | — | |
| TCLParadigm=Text/image alignment training with captions, Background Prompt=No2026.01 | 30.3 | — | |
| EVA-CLIP + UniRefinerViT=8B/14, Background category=Without background category, Protocol=Zero-shot2026.05 | 29.8 | — | |
| CLIP + UniRefinerViT=G/14, Background category=Without background category, Protocol=Zero-shot2026.05 | 28.1 | — | |
| MaskCLIPParadigm=Use Frozen CLIP, Extra Backbones=ref[9], Background Prompt=No2026.01 | 27.4 | — | |
| MaskCLIPParadigm=Use Frozen CLIP, Background Prompt=No2026.01 | 25.6 | — | |
| CLIPViT=G/14, Background category=Without background category, Protocol=Zero-shot2026.05 | 25.1 | — | |
| SigLIPv2ViT=So/16, Background category=Without background category, Protocol=Zero-shot2026.05 | 24.2 | — | |
| GroupViTParadigm=Text/image alignment training with captions, Background Prompt=No2026.01 | 23.4 | — | |
| ReCoParadigm=Build prototypes per class, Background Prompt=No2026.01 | 22.3 | — | |
| CLIP-DIYParadigm=Use Frozen CLIP, Extra Backbones=DINO, Background Prompt=No2026.01 | 19.8 | — | |
| EVA-CLIPViT=8B/14, Background category=Without background category, Protocol=Zero-shot2026.05 | 16 | — |