Open-vocabulary Semantic Segmentation on Pascal VOC 21 (With Background)
74.8mIoUCorrCLIP
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CorrCLIPExtra Backbone=DINO+SAM2, Vision Model Configuration=Multi vision models2026.05 | 74.8 | 51 | 1,440 | 3,200 | |
| VIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 73.2 | 52.4 | 100 | 1,650 | |
| TridentExtra Backbone=DINO+SAM, Vision Model Configuration=Multi vision models2026.05 | 67.1 | 45.8 | 120 | 3,710 | |
| ProxyCLIP + GLA (Best)Train=False, External Model=DINO, DS Hyperparameter=True, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 66.7 | — | — | — | |
| CLIPerExtra Backbone=Stable Diffusion, Vision Model Configuration=Multi vision models2026.05 | 66.5 | 45.3 | 180 | 3,390 | |
| ProxyCLIP + GLATrain=False, External Model=DINO, DS Hyperparameter=False, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 66.3 | — | — | — | |
| FreeCPTrain=False, External Model=None, DS Hyperparameter=True, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 65.8 | — | — | — | |
| CASSTrain=False, External Model=DINO, DS Hyperparameter=True, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 65.8 | — | — | — | |
| CASSExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 65.8 | 44.4 | 440 | 2,890 | |
| SC-CLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 64.6 | 43.9 | 85 | 1,600 | |
| FreeCPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 64.5 | 42.2 | 120 | 750 | |
| DIH-CLIPTrain=False, External Model=None, DS Hyperparameter=False, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 64.2 | — | — | — | |
| SFPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 63.9 | 44 | 100 | 1,600 | |
| FSAExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 63.7 | 43.3 | 110 | 1,650 | |
| ProxyCLIP + GLATrain=False, External Model=DINO, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 63.4 | — | — | — | |
| ProxyCLIP + GLATrain=False, External Model=DINO, DS Hyperparameter=False, Image Resize=448, Crop size=336, Stride=112, Rename trick=With rename trick on Background Classes2026.03 | 63.2 | — | — | — | |
| LPOSSExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 62.4 | 42.1 | — | — | |
| CLIP-DINOiserTrain=True, External Model=DINO, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 62.2 | — | — | — | |
| LaVGTrain=False, External Model=None, DS Hyperparameter=False, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 62.1 | — | — | — | |
| LaVGExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 61.8 | 38.2 | 140 | 1,750 | |
| ProxyCLIPTrain=False, External Model=DINO, DS Hyperparameter=False, Image Resize=448, Crop size=336, Stride=112, Rename trick=With rename trick on Background Classes2026.03 | 61.3 | — | — | — | |
| ProxyCLIPExtra Backbone=DINO, Vision Model Configuration=Multi vision models2026.05 | 61.3 | 42.3 | 105 | 1,600 | |
| ResCLIPTrain=False, External Model=None, DS Hyperparameter=True, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 61.1 | — | — | — | |
| ResCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 60.9 | 41.2 | 85 | 2,550 | |
| CLIP-DIYTrain=False, External Model=None, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 59.9 | — | — | — | |
| SCLIP + GLATrain=False, External Model=None, DS Hyperparameter=False, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 59.8 | — | — | — | |
| SCLIPTrain=False, External Model=None, DS Hyperparameter=False, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 59.1 | — | — | — | |
| SCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 59.1 | 38.2 | 60 | 1,580 | |
| NACLIPTrain=False, External Model=None, DS Hyperparameter=False, Image Resize=336, Crop size=224, Stride=112, Rename trick=With multiple textual prompts per class2026.03 | 58.9 | — | — | — | |
| CdamCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 58.7 | — | 100 | 920 | |
| ClearCLIP + GLATrain=False, External Model=None, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 55.6 | — | — | — | |
| TCLTrain=True, External Model=None, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 55 | — | — | — | |
| ClearCLIPTrain=False, External Model=None, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 51.8 | — | — | — | |
| ClearCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 51.8 | 38.1 | 45 | 650 | |
| GroupViTTrain=True, External Model=None, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 50.4 | — | — | — | |
| MaskCLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 38.8 | 27.9 | — | — | |
| dino.txtExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 35.9 | 31.8 | 90 | 1,500 | |
| ReCoTrain=True, External Model=None, DS Hyperparameter=False, Image Resize=448, Crop size=448, Stride=224, Rename trick=None2026.03 | 25.1 | — | — | — | |
| CLIPExtra Backbone=X, Vision Model Configuration=Single vision model2026.05 | 16.2 | 11.6 | — | — |