| instance-segmentation-on-ade20k-val | OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained) | #1 | AP: 44.2APL: 64.3APM: 49.9APS: 23.7 |
| instance-segmentation-on-ade20k-val | OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain) | #4 | AP: 40.2APL: 59.7APM: 44.4APS: 19.2 |
| instance-segmentation-on-ade20k-val | OneFormer (DiNAT-L, single-scale) | #7 | AP: 36.0 |
| instance-segmentation-on-ade20k-val | OneFormer (Swin-L, single-scale) | #8 | AP: 35.9 |
| instance-segmentation-on-cityscapes-val | OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained) | #2 | mask AP: 48.7 |
| instance-segmentation-on-cityscapes-val | OneFormer (DiNAT-L, single-scale) | #5 | mask AP: 45.6 |
| instance-segmentation-on-cityscapes-val | OneFormer (Swin-L, single-scale) | #6 | mask AP: 45.6 |
| instance-segmentation-on-coco-val-panoptic | OneFormer (InternImage-H, emb_dim=1024, single-scale) | #1 | AP: 52.0 |
| instance-segmentation-on-coco-val-panoptic | OneFormer (DiNAT-L, single-scale) | #2 | AP: 49.2 |
| instance-segmentation-on-coco-val-panoptic | OneFormer (Swin-L, single-scale) | #4 | AP: 49.0 |
| panoptic-segmentation-on-ade20k-val | OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896) | #1 | PQ: 54.5mIoU: 60.4AP: 40.2 |
| panoptic-segmentation-on-ade20k-val | OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-Pretrain) | #4 | PQ: 53.4mIoU: 58.9 |
| panoptic-segmentation-on-ade20k-val | OneFormer (DiNAT-L, single-scale, 1280x1280) | #8 | PQ: 51.5mIoU: 58.3AP: 37.1 |
| panoptic-segmentation-on-ade20k-val | OneFormer (Swin-L, single-scale, 1280x1280) | #9 | PQ: 51.4mIoU: 57.0AP: 37.8 |
| panoptic-segmentation-on-ade20k-val | OneFormer (DiNAT-L, single-scale, 640x640) | #11 | PQ: 50.5mIoU: 58.3AP: 36.0 |
| panoptic-segmentation-on-ade20k-val | OneFormer (ConvNeXt-XL, single-scale, 640x640) | #12 | PQ: 50.1mIoU: 57.4AP: 36.3 |
| panoptic-segmentation-on-ade20k-val | OneFormer (ConvNeXt-L, single-scale, 640x640) | #13 | PQ: 50.0mIoU: 56.6AP: 36.2 |
| panoptic-segmentation-on-ade20k-val | OneFormer (Swin-L, single-scale, 640x640) | #14 | PQ: 49.8mIoU: 57.0AP: 35.9 |
| panoptic-segmentation-on-cityscapes-test | OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained) | #1 | PQ: 68.0 |
| panoptic-segmentation-on-cityscapes-val | OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) | #2 | PQ: 70.1PQst: 74.1PQth: 64.6mIoU: 84.6AP: 48.7 |
| panoptic-segmentation-on-cityscapes-val | OneFormer (ConvNeXt-L, single-scale) | #3 | PQ: 68.51mIoU: 83.0AP: 46.5 |
| panoptic-segmentation-on-cityscapes-val | OneFormer (ConvNeXt-XL, single-scale) | #6 | PQ: 68.4mIoU: 83.6AP: 46.7 |
| panoptic-segmentation-on-cityscapes-val | OneFormer (DiNAT-L, single-scale) | #8 | PQ: 67.6mIoU: 83.1AP: 45.6 |
| panoptic-segmentation-on-cityscapes-val | OneFormer (Swin-L, single-scale) | #11 | PQ: 67.2mIoU: 83.0AP: 45.6 |
| panoptic-segmentation-on-coco-minival | OneFormer (InternImage-H,single-scale) | #2 | PQ: 60.0PQst: 49.2PQth: 67.1AP: 52.0mIoU: 68.8 |
| panoptic-segmentation-on-coco-minival | OneFormer (DiNAT-L, single-scale) | #14 | PQ: 58.0PQst: 48.4PQth: 64.3AP: 49.2mIoU: 68.1 |
| panoptic-segmentation-on-coco-minival | OneFormer (Swin-L, single-scale) | #17 | PQ: 57.9PQst: 48.0PQth: 64.4AP: 49.0mIoU: 67.4 |
| panoptic-segmentation-on-mapillary-val | OneFormer (DiNAT-L, single-scale) | #1 | PQ: 46.7mIoU: 61.7PQst: 54.9PQth: 40.5 |
| panoptic-segmentation-on-mapillary-val | OneFormer (ConvNeXt-L, single-scale) | #2 | PQ: 46.4mIoU: 61.6PQst: 54.0PQth: 40.6 |
| semantic-segmentation-on-ade20k-val | OneFormer (InternImage-H, emb_dim=256, multi-scale, 896x896) | #6 | mIoU: 60.8 |
| semantic-segmentation-on-ade20k-val | OneFormer (DiNAT-L, multi-scale, 896x896) | #9 | mIoU: 58.6 |
| semantic-segmentation-on-ade20k-val | OneFormer (DiNAT-L, multi-scale, 640x640) | #11 | mIoU: 58.4 |
| semantic-segmentation-on-ade20k-val | OneFormer (Swin-L, multi-scale, 896x896) | #13 | mIoU: 58.3 |
| semantic-segmentation-on-ade20k-val | OneFormer (Swin-L, multi-scale, 640x640) | #18 | mIoU: 57.7 |
| semantic-segmentation-on-cityscapes-val | OneFormer (ConvNeXt-XL, Mapillary, multi-scale) | #10 | mIoU: 85.8 |
| semantic-segmentation-on-cityscapes-val | OneFormer (ConvNeXt-XL, multi-scale) | #13 | mIoU: 84.6 |
| semantic-segmentation-on-cityscapes-val | OneFormer (Swin-L, multi-scale) | #15 | mIoU: 84.4 |
| semantic-segmentation-on-coco-1 | OneFormer (InternImage-H, emb_dim=1024, single-scale) | #3 | mIoU: 68.8 |
| semantic-segmentation-on-coco-1 | OneFormer (DiNAT-L, single-scale) | #5 | mIoU: 68.1 |
| semantic-segmentation-on-coco-1 | OneFormer (Swin-L, single-scale) | #7 | mIoU: 67.4 |
| semantic-segmentation-on-mapillary-val | OneFormer (DiNAT-L, multi-scale) | #2 | mIoU: 64.9 |