Unsupervised Semantic Segmentation On Suim
评估指标
Pixel Accuracy
mIoU
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | |||
|---|---|---|---|---|
| DatUS (ViT-B/8) + OC | 69.98 | 34.02 | DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer | |
| GraPix + AUT | 65.48 | 30.78 | GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel Clustering | - |
| 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.