Semantic Segmentation on Dv-58 Synthetic-to-Real (test)
55.4ACDC-41 ScoreS2-Corr
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| S2-CorrBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 55.4 | 59.8 | 41.5 | 40.8 | 49.4 | |
| CAT-Seg+DGInStyleBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 53.7 | 59 | 37.9 | 38 | 47.2 | |
| CAT-SegBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 53.6 | 59.7 | 41.1 | 38.2 | 48.2 | |
| MaskAdapterBackbone=EVA02 ViT-L/14, Training Data=GTA-72026.02 | 52.1 | 55.9 | 37.1 | 37.1 | 45.6 | |
| S2-CorrBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 51.3 | 56.4 | 42.4 | 36.7 | 46.7 | |
| CAT-SegBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 51.2 | 56.2 | 39.3 | 35.7 | 45.6 | |
| CLIPSelfBackbone=EVA02 ViT-L/14, Training Data=GTA-7+COCO2026.02 | 51.2 | 59.7 | 40.6 | 39.7 | 48 | |
| RSC-CLIPSelfBackbone=EVA02 ViT-B/16, Training Data=GTA-7+COCO2026.02 | 51.1 | 50.7 | 40.3 | 32 | 43.5 | |
| CAT-Seg+DGInStyleBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 50.7 | 55.9 | 39.6 | 34 | 45.1 | |
| CLIPSelfBackbone=EVA02 ViT-B/16, Training Data=GTA-7+COCO2026.02 | 50.6 | 52.1 | 40.4 | 34.6 | 44.4 | |
| MaskAdapterBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 50.1 | 49.2 | 38.1 | 32.7 | 42.5 | |
| ESC-NetBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 49.4 | 52.4 | 37.9 | 33.3 | 43.3 | |
| CAT-Seg+AdvStyleBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 49.2 | 54.2 | 39.1 | 34.3 | 44.2 | |
| MAFT+Backbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 49.1 | 48.3 | 39.9 | 31.8 | 42.3 | |
| SANBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 47.7 | 49 | 37.8 | 30.3 | 41.2 | |
| OVSegBackbone=EVA02 ViT-B/16, Training Data=GTA-72026.02 | 45.1 | 52.6 | 35.5 | 32.9 | 41.5 |