Semantic Segmentation on NYUD
63.82mIoURADIOv2.5-H
Evaluation results
| Method | Links | |
|---|---|---|
| RADIOv2.5-HParams=653M2024.12 | 63.82 | |
| RADIOv2.5-gParams=1.1B2024.12 | 63.46 | |
| RADIOv2.1-HParams=653M2024.12 | 62.76 | |
| UNITParams=1B2024.12 | 61.62 | |
| UNITParams=632M2024.12 | 61.44 | |
| RADIOv2.5-LParams=320M2024.12 | 61.42 | |
| UNIC-LParams=307M2024.12 | 58.56 | |
| RADIOv2.5-BParams=98M2024.12 | 57.19 | |
| UNIC-BParams=86M2024.12 | 42.21 | |
| DenseCLPre-training Dataset=COCO, Pre-training Epochs=8002021.06 | 42.1 | |
| MoCo + CC + A+ + kNNPre-training Dataset=COCO, Pre-training Epochs=800, Constrained multi-crop=true, Stronger augmentations=true, kNN nearest neighbors=true2021.06 | 41.3 | |
| MoCo + CC + A+Pre-training Dataset=COCO, Pre-training Epochs=800, Constrained multi-crop=true, Stronger augmentations=true2021.06 | 40.7 | |
| MoCo + CCPre-training Dataset=COCO, Pre-training Epochs=800, Constrained multi-crop=true2021.06 | 40.4 | |
| VirTexPre-training Dataset=COCO captions2021.06 | 40.3 | |
| MoCoPre-training Dataset=COCO, Pre-training Epochs=8002021.06 | 40 | |
| TheiaParams=86M2024.12 | 38.9 | |
| Rand. init.2021.06 | 24.4 |