Referring Expression Segmentation On
Métriques
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Mean IoU | Paper Title | Repository | |||
|---|---|---|---|---|---|---|
| HULANet | 41.3 | 42.9 | 27.8 | 5.9 | PhraseCut: Language-based Image Segmentation in the Wild | - |
| GLIPv2 | 61.3 | - | - | - | GLIPv2: Unifying Localization and Vision-Language Understanding | - |
| RMI | 21.1 | 22 | 11.6 | 1.5 | PhraseCut: Language-based Image Segmentation in the Wild | - |
| GROUNDHOG | 54.5 | - | - | - | GROUNDHOG: Grounding Large Language Models to Holistic Segmentation | - |
| MDETR ENB3 | 53.7 | 57.5 | 39.9 | 11.9 | MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding | - |
| MattNet | 20.2 | 19.7 | 13.5 | 3 | PhraseCut: Language-based Image Segmentation in the Wild | - |
0 of 6 row(s) selected.