Unsupervised Semantic Segmentation With 11
Metriken
mIoU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | mIoU |
|---|---|
| ttd-text-tag-self-distillation-enhancing | 61.1 |
| learning-to-generate-text-grounded-mask-for | 55.0 |
| tagclip-a-local-to-global-framework-to | 68.7 |
| harnessing-vision-foundation-models-for-high | 70.8 |
| denseclip-extract-free-dense-labels-from-clip | 29.3 |
| tagalign-improving-vision-language-alignment | 53.9 |
| ttd-text-tag-self-distillation-enhancing | 43.1 |
| proxyclip-proxy-attention-improves-clip-for | 65.0 |