Semi Supervised Semantic Segmentation On 25
Metriken
mIoU (1% Labels)
mIoU (10% Labels)
mIoU (20% Labels)
mIoU (50% Labels)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | mIoU (1% Labels) | mIoU (10% Labels) | mIoU (20% Labels) | mIoU (50% Labels) |
|---|---|---|---|---|
| fidnet-lidar-point-cloud-semantic | 38.3 | 57.5 | 62.7 | 67.6 |
| mean-teachers-are-better-role-models-weight | 42.1 | 60.4 | 65.4 | 69.4 |
| semi-supervised-semantic-segmentation-with-3 | 40.7 | 60.8 | 64.9 | 68.0 |
| learning-from-spatio-temporal-correlation-for | 62.9 | 74.3 | 76 | 76.1 |
| unsupervised-domain-adaptation-for-semantic | 40.9 | 60.5 | 64.3 | 69.3 |
| cylindrical-and-asymmetrical-3d-convolution | 50.9 | 65.9 | 66.6 | 71.2 |
| learning-from-spatio-temporal-correlation-for | - | - | - | - |
| consistency-regularization-and-cutmix-for | 43.8 | 63.9 | 64.8 | 69.8 |
| lasermix-for-semi-supervised-lidar-semantic | 49.5 | 68.2 | 70.6 | 73.0 |
| mean-teachers-are-better-role-models-weight | 51.6 | 66.0 | 67.1 | 71.7 |
| lasermix-for-semi-supervised-lidar-semantic | 55.3 | 69.9 | 71.8 | 73.2 |