Panoptic Segmentation On Mapillary Val
Metrics
PQ
PQst
PQth
mIoU
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | PQ | PQst | PQth | mIoU |
|---|---|---|---|---|
| scaling-wide-residual-networks-for-panoptic | 44.8 | 51.9 | 39.3 | 60.0 |
| efficientps-efficient-panoptic-segmentation | 40.6 | - | - | - |
| fully-convolutional-networks-for-panoptic | 36.9 | - | 32.9 | - |
| oneformer-one-transformer-to-rule-universal | 46.7 | 54.9 | 40.5 | 61.7 |
| panoptic-deeplab-a-simple-strong-and-fast | 40.5 | - | - | - |
| panoptic-segmentation-with-a-joint-semantic | 17.6 | - | - | - |
| fully-convolutional-networks-for-panoptic | - | 42.3 | - | - |
| adaptis-adaptive-instance-selection-network | 40.3 | - | - | 56.8 |
| axial-deeplab-stand-alone-axial-attention-for | 41.1 | 51.3 | 33.4 | 58.4 |
| hierarchical-multi-scale-attention-for | 17.6 | - | - | - |
| fully-convolutional-networks-for-panoptic | 45.7 | 52.1 | 40.8 | - |
| oneformer-one-transformer-to-rule-universal | 46.4 | 54.0 | 40.6 | 61.6 |
| intra-batch-supervision-for-panoptic-1 | 42.2 | 52.0 | 34.9 | - |