Semantic Segmentation on VOC 21 (val)
76.4mIoUOV-Stitcher
Evaluation Results
| Method | Links | |
|---|---|---|
| OV-StitcherBackbone=ViT-B/16, VLM Source=MetaCLIP2026.04 | 76.4 | |
| OV-StitcherBackbone=ViT-B/16, VLM Source=OpenAI CLIP, post-processing=true2026.04 | 75.7 | |
| CorrCLIPBackbone=ViT-B/16, VLM Source=MetaCLIP2026.04 | 74.8 | |
| OV-StitcherBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 74 | |
| OV-StitcherBackbone=ViT-B/16, VLM Source=OpenAI CLIP, post-processing=false2026.04 | 73.1 | |
| CorrCLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP, post-processing=true2026.04 | 72.2 | |
| CorrCLIPBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 71.8 | |
| CorrCLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP, post-processing=false2026.04 | 69.2 | |
| TridentBackbone=ViT-B/16, VLM Source=MetaCLIP2026.04 | 68.4 | |
| TridentBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 67.1 | |
| CASSBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 65.8 | |
| SC-CLIPBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 65 | |
| SC-CLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 64.6 | |
| ProxyCLIPBackbone=ViT-B/16, VLM Source=MetaCLIP2026.04 | 63.3 | |
| SFPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 62.9 | |
| TridentBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 62.6 | |
| ProxyCLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 61.3 | |
| ResCLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 61.1 | |
| ProxyCLIPBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 60.6 | |
| SCLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 59.1 | |
| NACLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 58.9 | |
| ResCLIPBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 54.1 | |
| ClearCLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 51.8 | |
| CLIPtraseBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 50.9 | |
| MaskCLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 43.4 | |
| MaskCLIPBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 23.3 | |
| CLIPBackbone=ViT-B/16, VLM Source=OpenAI CLIP2026.04 | 18.6 | |
| CLIPBackbone=ViT-L/14, VLM Source=OpenAI CLIP2026.04 | 8.2 |