| instance-segmentation-on-ade20k-val | ViT-P (OneFormer, DiNAT-L, single-scale, 1280x1280, COCO_pretrain) | #3 | AP: 40.7 |
| instance-segmentation-on-ade20k-val | ViT-P (OneFormer, DiNAT-L, single-scale, 1280x1280) | #6 | AP: 37.8 |
| instance-segmentation-on-cityscapes-val | ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) | #1 | mask AP: 49.0AP: 49.0 |
| panoptic-segmentation-on-ade20k-val | ViT-P (OneFormer, DiNAT-L, single-scale, 1280x1280, COCO_pretrain) | #2 | PQ: 54.0 |
| panoptic-segmentation-on-ade20k-val | ViT-P (OneFormer, DiNAT-L, single-scale, 1280x1280) | #7 | PQ: 51.9 |
| panoptic-segmentation-on-cityscapes-val | ViT-P (OneFormer, InternImage-H) | #1 | PQ: 70.8mIoU: 85.4AP: 50.6 |
| semantic-segmentation-on-ade20k | ViT-P (InternImage-H) | #1 | Validation mIoU: 63.6Params (M): 1610 |
| semantic-segmentation-on-ade20k | ViT-P (OneFormer, InternImage-H) | #7 | Validation mIoU: 61.6Params (M): 1400 |
| semantic-segmentation-on-ade20k | ViT-P (OneFormer, DiNAT-L) | #16 | Validation mIoU: 59.9Params (M): 309 |
| semantic-segmentation-on-cityscapes-val | ViT-P (InternImage-H) | #1 | mIoU: 87.4 |
| semantic-segmentation-on-coco-1 | ViT-P (OneFormer, InternImage-H) | #2 | mIoU: 69.1 |
| semantic-segmentation-on-coco-1 | ViT-P (OneFormer, DiNAT-L) | #4 | mIoU: 68.8 |
| semantic-segmentation-on-coco-stuff-test | ViT-P (InternImage-H) | #1 | mIoU: 53.5 |