Panoptic Segmentation on SUNRGB-D (test)
48.3mIoUPanopticNDT (EMSANet-R34-NBt1D)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PanopticNDT (EMSANet-R34-NBt1D)Protocol=Fine-tuning, LR=0.002, Selection=Best in run2023.09 | 48.3 | 52.48 | 60.03 | 86.39 | 13 | |
| PanopticNDT (EMSANet-R34-NBt1D)Protocol=Fine-tuning, LR=0.002, Selection=Best on SUNRGB-D2023.09 | 47.88 | 52.48 | 60.03 | 86.3 | 13.02 | |
| PanopticNDT (EMSANet-R34-NBt1D)Protocol=Application network, LR=0.0005, Selection=Best on SUNRGB-D2023.09 | 47.32 | 50.91 | 58.4 | 86.06 | 14.28 | |
| PanopticNDT (EMSANet-R34-NBt1D)Protocol=Application network, LR=0.0005, Selection=Best in run2023.09 | 47.32 | 50.91 | 58.4 | 86.22 | 14.19 | |
| EMSAFormerBackbone=SwinV2-T-128, Augmentation Strategy=Multi-Aug, Decoder Configuration=Sem(SegFormer)2023.06 | 45.94 | 51.7 | 60.15 | 84.65 | 13.9 | |
| EMSANetBackbone=2x ResNet34-NBt1D2023.06 | 45.66 | 50.53 | 58.66 | 85.2 | 14.15 | |
| EMSAFormerBackbone=SwinV2-T-128, Augmentation Strategy=Multi-Aug2023.06 | 45.27 | 50.08 | 59.08 | 84.83 | 14.93 | |
| EMSANetBackbone=2x ResNet1012023.06 | 44.19 | 51.75 | 59.74 | 85.64 | 13 |