| Paper | Code | Mean IoU | Pr@0.5 | Pr@0.7 | Pr@0.9 | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|
| GLIPv2: Unifying Localization and Vision-Language Understanding | ✓ Link | 61.3 | GLIPv2 | 2022-06-12 | |||
| GROUNDHOG: Grounding Large Language Models to Holistic Segmentation | 54.5 | GROUNDHOG | 2024-02-26 | ||||
| MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding | ✓ Link | 53.7 | 57.5 | 39.9 | 11.9 | MDETR ENB3 | 2021-04-26 |
| PhraseCut: Language-based Image Segmentation in the Wild | ✓ Link | 41.3 | 42.9 | 27.8 | 5.9 | HULANet | 2020-08-03 |
| PhraseCut: Language-based Image Segmentation in the Wild | ✓ Link | 21.1 | 22 | 11.6 | 1.5 | RMI | 2020-08-03 |
| PhraseCut: Language-based Image Segmentation in the Wild | ✓ Link | 20.2 | 19.7 | 13.5 | 3 | MattNet | 2020-08-03 |