Panoptic Segmentation on MS-COCO
58.5PQDINAT-L
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DINAT-LBackbone=DINAT-L, Win. Size=11 x 11, # of Params=220 M, FLOPs=540 G, Pre-trained=ImageNet-22K, Resolution=800x800, Framework=Mask2Former2022.09 | 58.5 | 64.9 | 48.8 | 49.2 | 68.3 | |
| Swin-LBackbone=Swin-L, Win. Size=12 x 12, # of Params=216 M, FLOPs=658 G, Pre-trained=ImageNet-22K, Resolution=800x800, Framework=Mask2Former2022.09 | 57.8 | 64.2 | 48.1 | 48.6 | 67.4 | |
| HIPIEOpen Vocabulary=true, Unified Framework=true2023.07 | 1.3 | — | — | — | — |