Semantic Segmentation on ADE20K (mIoU-fg)
13.8mIoU-fgPAL
Evaluation results
| Method | Links | |
|---|---|---|
| PALVisual Backbone=DINOv2 ViT-L, Text Encoder=RoBERTa-Large, Evaluation Protocol=Zero-shot2026.05 | 13.8 | |
| FAVisual Backbone=DINOv2 ViT-L, Text Encoder=RoBERTa-Large, Evaluation Protocol=Zero-shot2026.05 | 11.9 | |
| SAILVisual Backbone=DINOv2 ViT-L, Text Encoder=RoBERTa-Large, Evaluation Protocol=Zero-shot2026.05 | 10.7 | |
| MLPRSVisual Backbone=DINOv2 ViT-L, Text Encoder=RoBERTa-Large, Evaluation Protocol=Zero-shot2026.05 | 3.8 | |
| LinearRSVisual Backbone=DINOv2 ViT-L, Text Encoder=RoBERTa-Large, Evaluation Protocol=Zero-shot2026.05 | 3.7 |