| open-vocabulary-semantic-segmentation-on-ade20k-150 | X-Agent (CLIP ViT-B/16) | – | mIoU: 32.1 |
| open-vocabulary-semantic-segmentation-on-ade20k-150 | X-Agent (CLIP ViT-L/14) | – | mIoU: 38.2 |
| open-vocabulary-semantic-segmentation-on-ade20k-847 | X-Agent (CLIP ViT-B/16) | – | mIoU: 11.9 |
| open-vocabulary-semantic-segmentation-on-ade20k-847 | X-Agent (CLIP ViT-L/14) | – | mIoU: 16.0 |
| open-vocabulary-semantic-segmentation-on-pascal-context-459 | X-Agent (CLIP ViT-B/16) | – | mIoU: 19.2 |
| open-vocabulary-semantic-segmentation-on-pascal-context-459 | X-Agent (CLIP ViT-L/14) | – | mIoU: 24.2 |
| open-vocabulary-semantic-segmentation-on-pascal-context-59 | X-Agent (CLIP ViT-B/16) | – | mIoU: 57.7 |
| open-vocabulary-semantic-segmentation-on-pascal-context-59 | X-Agent (CLIP ViT-L/14) | – | mIoU: 63.7 |