| Benchmark | Model | Rank | Results |
|---|---|---|---|
| open-vocabulary-semantic-segmentation-on-coco-stuff-171 | POMP | #1 | HIoU: 39.1 |
| prompt-engineering-on-imagenet-a | POMP | #3 | Top-1 accuracy %: 51.6 |
| prompt-engineering-on-imagenet-r | POMP | #5 | Top-1 accuracy %: 77.9 |
| prompt-engineering-on-imagenet-s | POMP | #6 | Top-1 accuracy %: 49.8 |
| open-vocabulary-semantic-segmentation-on-pascalvoc-20 | POMP | #13 | mIoU: 89.4hIoU: 84.4 |
| open-vocabulary-object-detection-on-lvis-v1-0 | POMP | #17 | AP novel-LVIS base training: 25.2 |