| unsupervised-semantic-segmentation-on-cityscapes | PriMaPs-EM + STEGO (DINO ViT-B/8) | #4 | mIoU: 21.6Accuracy: 78.6 |
| unsupervised-semantic-segmentation-on-cityscapes | PriMaPs-EM (DINO ViT-S/8) | #7 | mIoU: 19.4Accuracy: 81.2 |
| unsupervised-semantic-segmentation-on-coco-stuff-27 | PriMaPs+STEGO (DINO ViT-B/8) | #6 | Clustering [mIoU]: 29.7Clustering [Accuracy]: 57.9 |
| unsupervised-semantic-segmentation-on-coco-stuff-27 | PriMaPs+HP (DINO ViT-S/8) | #12 | Clustering [mIoU]: 25.1Clustering [Accuracy]: 57.8 |
| unsupervised-semantic-segmentation-on-potsdam-3 | PriMaPs-EM+HP (DINO ViT-B/8) | #2 | Accuracy: 83.3mIoU: 71.0 |
| unsupervised-semantic-segmentation-on-potsdam-3 | PriMaPs-EM (DINO ViT-B/8) | #4 | Accuracy: 80.5mIoU: 67.0 |