Referring Expression Segmentation On
Metrics
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Mean IoU | [email protected] | [email protected] | [email protected] |
|---|---|---|---|---|
| phrasecut-language-based-image-segmentation-1 | 41.3 | 42.9 | 27.8 | 5.9 |
| glipv2-unifying-localization-and-vision | 61.3 | - | - | - |
| phrasecut-language-based-image-segmentation-1 | 21.1 | 22 | 11.6 | 1.5 |
| groundhog-grounding-large-language-models-to | 54.5 | - | - | - |
| mdetr-modulated-detection-for-end-to-end | 53.7 | 57.5 | 39.9 | 11.9 |
| phrasecut-language-based-image-segmentation-1 | 20.2 | 19.7 | 13.5 | 3 |