Semantic Segmentation on Hypersim
37mIoUMultiMAE
Evaluation results
| Method | Links | |
|---|---|---|
| MultiMAEInput Modality=RGB, Training Mode=Fine-tuning, Pre-training Dataset=ImageNet-1K2022.04 | 37 | |
| MAEInput Modality=RGB, Training Mode=Fine-tuning, Pre-training Dataset=ImageNet-1K2022.04 | 36.5 | |
| SupervisedInput Modality=RGB, Training Mode=Fine-tuning, Pre-training Dataset=ImageNet-1K2022.04 | 33.9 | |
| DINOInput Modality=RGB, Training Mode=Fine-tuning, Pre-training Dataset=ImageNet-1K2022.04 | 32.5 | |
| MoCo-v3Input Modality=RGB, Training Mode=Fine-tuning, Pre-training Dataset=ImageNet-1K2022.04 | 31.7 |