Unsupervised Semantic Segmentation On Coco 8
Metrics
Pixel Accuracy
mIoU
Results
Performance results of various models on this benchmark
Model Name | Pixel Accuracy | mIoU | Paper Title | Repository |
|---|---|---|---|---|
| TransFGU (ViT-S/8) | 64.3 | 12.7 | TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation | - |
| MaskContrast (ResNet-50) | 8.8 | 3.7 | Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals | - |
| CAUSE-TR (ViT-S/8) | 75.2 | 21.2 | Causal Unsupervised Semantic Segmentation | - |
| CAUSE-MLP (ViT-S/8) | 78.8 | 19.1 | Causal Unsupervised Semantic Segmentation | - |
0 of 4 row(s) selected.