Semantic Segmentation on PASCAL 1/16
78.5mIoUCLIP-Guided SAM
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIP-Guided SAMFine-tuning SAM?=Yes, VLM Size=87M (CS-CLIP-Base)2026.05 | 78.5 | |
| GroundedSAMFine-tuning SAM?=No, VLM Size=172M (GroundingDINO)2026.05 | 72 | |
| CLIPSurgery+SAMFine-tuning SAM?=Yes (adapters + decoder), VLM Size=87M (CS-CLIP-Base)2026.05 | 61.4 | |
| CLIPSurgery+SAMFine-tuning SAM?=Yes (decoder), VLM Size=87M (CS-CLIP-Base)2026.05 | 58.8 | |
| CLIPSurgery+SAM (modified)Fine-tuning SAM?=No, VLM Size=87M (CS-CLIP-Base)2026.05 | 48.6 | |
| CLIPSurgery+SAM (vanilla)Fine-tuning SAM?=No, VLM Size=87M (CS-CLIP-Base)2026.05 | 41.2 |