Object Detection on ADE20K (val)
46.9box APOpenSeeD (L)
Evaluation results
| Method | Links | |
|---|---|---|
| OpenSeeD (L)Type=Open-vocabulary, Backbone=Large, Image Size=1280x12802023.03 | 46.9 | |
| OpenSeeD (L)Type=Open-vocabulary, Backbone=Large2023.03 | 46.4 | |
| OpenSeeD (T)Type=Open-vocabulary, Backbone=Tiny2023.03 | 39.4 | |
| Mask2Former (L)Type=Closed-set, Backbone=Large2023.03 | 36.4 | |
| Mask2Former (T)Type=Closed-set, Backbone=Tiny2023.03 | 28.8 | |
| X-Decoder (T)Type=Open-vocabulary, Backbone=Tiny2023.03 | 28.8 |