Referring Expression Segmentation On Refcoco 4
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 |
|---|---|
| multi-task-visual-grounding-with-coarse-to | 77.96 |
| universal-segmentation-at-arbitrary | 78.29 |
| see-through-text-grouping-for-referring-image | 52.33 |
| gres-generalized-referring-expression-1 | 71.02 |
| maskris-semantic-distortion-aware-data | 74.46 |
| densely-connected-parameter-efficient-tuning | 78.6 |
| cris-clip-driven-referring-image-segmentation | 68.08 |
| mask-grounding-for-referring-image | 71.32 |
| vlt-vision-language-transformer-and-query | 68.43 |
| comprehensive-multi-modal-interactions-for | 58.46 |
| groundhog-grounding-large-language-models-to | 75.0 |
| lavt-language-aware-vision-transformer-for | 68.38 |
| mail-a-unified-mask-image-language-trimodal | 65.92 |
| hyperseg-towards-universal-visual | 83.5 |
| safari-adaptive-sequence-transformer-for | 74.53 |
| mattnet-modular-attention-network-for | 52.39 |
| referring-image-segmentation-via-cross-modal-1 | 53.44 |
| polyformer-referring-image-segmentation-as | 72.89 |
| improving-referring-image-segmentation-using | - |
| cross-modal-self-attention-network-for | 47.60 |
| bi-directional-relationship-inferring-network | 52.87 |
| polyformer-referring-image-segmentation-as | 74.56 |
| universal-instance-perception-as-object | 76.42 |
| refvos-a-closer-look-at-referring-expressions | 49.73 |
| vision-language-transformer-and-query | 59.20 |
| evf-sam-early-vision-language-fusion-for-text | 78.3 |
| multi-label-cluster-discrimination-for-visual | 82.9 |
| maskris-semantic-distortion-aware-data | 75.15 |
| universal-segmentation-at-arbitrary | 77.02 |