Zero Shot Segmentation On Ade20K Training
Metrics
mIoU
Results
Performance results of various models on this benchmark
Model Name | mIoU | Paper Title | Repository |
|---|---|---|---|
| MaskCLIP | 10.2 | Extract Free Dense Labels from CLIP | |
| GEM (MetaCLIP) | 17.1 | Grounding Everything: Emerging Localization Properties in Vision-Language Transformers | |
| CLIPSurgery | 12.9 | A Closer Look at the Explainability of Contrastive Language-Image Pre-training | |
| COSMOS ViT-B/16 | 17.7 | COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training | |
| GEM (CLIP) | 15.7 | Grounding Everything: Emerging Localization Properties in Vision-Language Transformers |
0 of 5 row(s) selected.