Semantic Segmentation On Kitti 360
Metrics
mIoU
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | mIoU |
|---|---|
| multi-modal-fusion-transformer-for-end-to-end | 56.57 |
| cmx-cross-modal-fusion-for-rgb-x-semantic | 64.31 |
| multimodal-token-fusion-for-vision | 54.55 |
| acnet-attention-based-network-to-exploit | 61.57 |
| hrfuser-a-multi-resolution-sensor-fusion | 48.74 |
| multimodal-token-fusion-for-vision | 57.44 |
| hrfuser-a-multi-resolution-sensor-fusion | 49.32 |
| hspformer-hierarchical-spatial-perception | 67.32 |
| cmx-cross-modal-fusion-for-rgb-x-semantic | 64.43 |
| depth-matters-exploring-deep-interactions-of | 68.74 |
| hspformer-hierarchical-spatial-perception | 66.82 |
| delivering-arbitrary-modal-semantic | 67.84 |
| issafe-improving-semantic-segmentation-in | 53.95 |
| issafe-improving-semantic-segmentation-in | 56.64 |
| perception-aware-multi-sensor-fusion-for-3d | 54.48 |
| hrfuser-a-multi-resolution-sensor-fusion | 52.61 |
| glass-segmentation-using-intensity-and | 48.51 |