| AUNet (ResNet-101-FPN) | 45.2 | 31.3 | 54.4 | Attention-guided Unified Network for Panoptic Segmentation | - |
| REFINE (ResNet-101-DCN) | 49.6 | 37.7 | 57.5 | REFINE: Prediction Fusion Network for Panoptic Segmentation | - |
| CMT-DeepLab (single-scale) | 55.7 | 46.8 | 61.6 | CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation | |
| Axial-DeepLab-L (multi-scale) | 44.2 | 36.8 | 49.2 | Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation | |
| Panoptic-DeepLab (Xception-71) | 41.4 | 35.9 | 45.1 | Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation | |
| AdaptIS (ResNeXt-101) | 42.8 | 31.8 | 50.1 | AdaptIS: Adaptive Instance Selection Network | |
| Panoptic-DeepLab (SWideRNet-[1, 1, 4], multi-scale) | 46.5 | 38.2 | 52.0 | Scaling Wide Residual Networks for Panoptic Segmentation | - |
| K-Net (Swin-L) | 55.2 | 46.2 | 61.2 | K-Net: Towards Unified Image Segmentation | |
| REFINE (ResNeXt-101-DCN) | 51.5 | 39.2 | 59.6 | REFINE: Prediction Fusion Network for Panoptic Segmentation | - |
| Panoptic SegFormer (ResNet-101) | 50.9 | 43.0 | 56.2 | Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers | |
| MaX-DeepLab-L (single-scale) | 51.3 | 42.4 | 57.2 | MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers | |
| AUNet (ResNet-152-FPN) | 45.5 | 31.6 | 54.7 | Attention-guided Unified Network for Panoptic Segmentation | - |
| OCFusion (ResNeXt-101-FPN) | 46.6 | 35.7 | 54.0 | Learning Instance Occlusion for Panoptic Segmentation | |
| K-Net (R101-FPN-DCN) | 48.3 | 39.7 | 54 | K-Net: Towards Unified Image Segmentation | |
| Panoptic FCN*++ (DCN-101-FPN) | 47.5 | 38.2 | 53.7 | Fully Convolutional Networks for Panoptic Segmentation | |
| MaskConver (ResNet50, single-scale) | 53.6 | 58.9 | 45.6 | MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation | |