Referring Expression Segmentation On Refcocog 1
评估指标
Overall IoU
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Overall IoU |
|---|---|
| groundhog-grounding-large-language-models-to | 74.6 |
| safari-adaptive-sequence-transformer-for | 71.06 |
| universal-segmentation-at-arbitrary | 79.47 |
| evf-sam-early-vision-language-fusion-for-text | 77.4 |
| maskris-semantic-distortion-aware-data | 66.5 |
| improving-referring-image-segmentation-using | - |
| polyformer-referring-image-segmentation-as | 70.19 |
| polyformer-referring-image-segmentation-as | 69.05 |
| vision-language-transformer-and-query | 56.65 |
| mask-grounding-for-referring-image | 66.03 |
| densely-connected-parameter-efficient-tuning | 75.3 |
| universal-segmentation-at-arbitrary | 80.54 |
| maskris-semantic-distortion-aware-data | 71.09 |
| hyperseg-towards-universal-visual | 78.9 |
| multi-task-visual-grounding-with-coarse-to | 76.39 |
| lavt-language-aware-vision-transformer-for | 62.09 |
| multi-label-cluster-discrimination-for-visual | 80.5 |