Referring Expression Segmentation On Refcoco 8
評価指標
mIoU
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 | mIoU |
|---|---|
| improving-referring-image-segmentation-using | 79.64 |
| evf-sam-early-vision-language-fusion-for-text | - |
| safari-adaptive-sequence-transformer-for | - |
| evp-enhanced-visual-perception-using-inverse | - |
| densely-connected-parameter-efficient-tuning | - |
| maskris-semantic-distortion-aware-data | - |
| multi-label-cluster-discrimination-for-visual | - |
| maskris-semantic-distortion-aware-data | - |
| hyperseg-towards-universal-visual | - |
| mask-grounding-for-referring-image | - |
| multi-task-visual-grounding-with-coarse-to | - |
| seqtr-a-simple-yet-universal-network-for | - |