Referring Expression Segmentation On Refcoco 5
評価指標
Overall IoU
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Overall IoU |
|---|---|
| mail-a-unified-mask-image-language-trimodal | 56.06 |
| hyperseg-towards-universal-visual | 75.2 |
| universal-instance-perception-as-object | 66.22 |
| maskris-semantic-distortion-aware-data | 59.39 |
| polyformer-referring-image-segmentation-as | 61.87 |
| mattnet-modular-attention-network-for | 40.08 |
| vlt-vision-language-transformer-and-query | 56.92 |
| cris-clip-driven-referring-image-segmentation | 53.68 |
| improving-referring-image-segmentation-using | - |
| safari-adaptive-sequence-transformer-for | 64.88 |
| mask-grounding-for-referring-image | 58.14 |
| cross-modal-self-attention-network-for | 37.89 |
| evf-sam-early-vision-language-fusion-for-text | 70.1 |
| see-through-text-grouping-for-referring-image | 40.41 |
| polyformer-referring-image-segmentation-as | 59.33 |
| densely-connected-parameter-efficient-tuning | 70.2 |
| lavt-language-aware-vision-transformer-for | 55.1 |
| universal-segmentation-at-arbitrary | 66.99 |
| universal-segmentation-at-arbitrary | 68.15 |
| maskris-semantic-distortion-aware-data | 62.83 |
| multi-task-visual-grounding-with-coarse-to | 68.95 |
| groundhog-grounding-large-language-models-to | 64.9 |
| refvos-a-closer-look-at-referring-expressions | 36.17 |
| vision-language-transformer-and-query | 49.36 |
| gres-generalized-referring-expression-1 | 57.65 |
| comprehensive-multi-modal-interactions-for | 44.12 |
| multi-label-cluster-discrimination-for-visual | 75.6 |
| referring-image-segmentation-via-cross-modal-1 | 43.23 |
| bi-directional-relationship-inferring-network | 42.13 |