Unsupervised Semantic Segmentation On Suim
Metrics
Pixel Accuracy
mIoU
Results
Performance results of various models on this benchmark
Model Name | Pixel Accuracy | mIoU | Paper Title | Repository |
|---|---|---|---|---|
| GraPix + AUT | 65.48 | 30.78 | GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel Clustering | |
| DatUS (ViT-B/8) + OC | 69.98 | 34.02 | DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer | |
| DatUS (ViT-B/8) | 64.67 | 28.48 | DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer | |
| GraPix | 64.06 | 28.98 | GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel Clustering |
0 of 4 row(s) selected.