Semantic Segmentation On Hypersim
Metrics
mIoU
Results
Performance results of various models on this benchmark
Model Name | mIoU | Paper Title | Repository |
|---|---|---|---|
| DINO (ViT-B) | 32.5 | MultiMAE: Multi-modal Multi-task Masked Autoencoders | |
| EMSANet (2x ResNet-34 NBt1D) | 49.74 | PanopticNDT: Efficient and Robust Panoptic Mapping | |
| MoCo-v3 (ViT-B) | 31.7 | MultiMAE: Multi-modal Multi-task Masked Autoencoders | |
| MultiMAE (ViT-B) | 37.0 | MultiMAE: Multi-modal Multi-task Masked Autoencoders | |
| MAE (ViT-B) | 36.5 | MultiMAE: Multi-modal Multi-task Masked Autoencoders |
0 of 5 row(s) selected.