Open-Vocabulary Semantic Segmentation on Pascal Context PC59 without background
48.8mIoUCorrCLIP
Evaluation results
| Method | Links | ||
|---|---|---|---|
| CorrCLIPExtra Backbone=DINO+SAM2, Vision Model Configuration=Multi vision models2026.05 | 48.8 | 51 | |
| VIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 46.5 | 52.4 | |
| CLIPerExtra Backbone=Stable Diffusion, Vision Model Configuration=Multi vision models2026.05 | 42.4 | 45.3 | |
| TridentExtra Backbone=DINO+SAM, Vision Model Configuration=Multi vision models2026.05 | 42.2 | 45.8 | |
| CASSExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 40.2 | 44.4 | |
| SC-CLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 40.1 | 43.9 | |
| FSAExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 39.9 | 43.3 | |
| SFPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 39.9 | 44 | |
| FreeCPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 39.3 | 42.2 | |
| ProxyCLIPExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 39.1 | 42.3 | |
| LPOSSExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 38.6 | 42.1 | |
| ResCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 36.6 | 41.2 | |
| ClearCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 35.9 | 38.1 | |
| LaVGExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 34.6 | 38.2 | |
| SCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 34.2 | 38.2 | |
| MaskCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 26.4 | 27.9 | |
| dino.txtExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 26.1 | 31.8 | |
| CLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 9.2 | 11.6 |