Semantic Segmentation on Dv-19 Synthetic-to-Real (test)
52.2CS-19 ScoreS2-Corr
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| S2-CorrBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 52.2 | 44.2 | 50.3 | 53.3 | 49.9 | |
| S2-CorrBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 49.3 | 40.4 | 48.6 | 54.5 | 48.2 | |
| CAT-SegBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 48.7 | 42.4 | 47.9 | 50.8 | 47.5 | |
| CLIPSelfBackbone=EVA02 ViT-B/16, Training Data=GTA-7+COCO2026.02 | 48.1 | 37.6 | 47.9 | 51.1 | 46.2 | |
| MaskAdapterBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 47.9 | 40.4 | 47.2 | 50.4 | 46.5 | |
| CLIPSelfBackbone=EVA02 ViT-L/14, Training Data=GTA-7+COCO2026.02 | 47.8 | 43.1 | 50 | 50.1 | 47.8 | |
| RSC-CLIPSelfBackbone=EVA02 ViT-B/16, Training Data=GTA-7+COCO2026.02 | 46.2 | 37.9 | 46 | 51.6 | 45.4 | |
| MaskAdapterBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 46 | 36.4 | 45.7 | 50.1 | 44.6 | |
| CAT-Seg+DGInStyleBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 46 | 43.9 | 48.9 | 51 | 47.5 | |
| MAFT+Backbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 45.7 | 38.5 | 43.7 | 50.2 | 44.5 | |
| CAT-Seg+AdvStyleBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 44.9 | 38.2 | 43.8 | 51.1 | 44.5 | |
| CAT-Seg+DGInStyleBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 44.4 | 39.1 | 48.1 | 51.4 | 45.8 | |
| CAT-SegBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 43.7 | 37.6 | 45.4 | 48.8 | 43.9 | |
| SANBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 43.3 | 36.7 | 42 | 48.1 | 42.5 | |
| ESC-NetBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 42.2 | 35.9 | 44.6 | 48.1 | 42.7 | |
| OVSegBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 41.2 | 34.9 | 42.5 | 45.1 | 40.9 |