Semantic Segmentation on Pascal VOC 20b
84.6mIoUODISE
Evaluation results
| Method | Links | |
|---|---|---|
| ODISEBackbone=ViT-L/14, Training Dataset=COCO-Panoptic2026.03 | 84.6 | |
| PCA-SegBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.03 | 84.4 | |
| DeCLIPBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.03 | 83.9 | |
| H-CLIPBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.03 | 83.2 | |
| PCA-SegBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.03 | 82.7 | |
| CAT-SegBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.03 | 82.5 | |
| DeCLIPBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.03 | 81.3 | |
| H-CLIPBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.03 | 78.2 | |
| CAT-SegBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.03 | 77.3 | |
| ZegFormerBackbone=ViT-B/16, Training Dataset=COCO-Stuff-1562026.03 | 62.7 | |
| LSeg+Backbone=ALIGN, Training Dataset=COCO-Stuff2026.03 | 59 |