Unsupervised Semantic Segmentation With 7
Métriques
mIoU
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | mIoU |
|---|---|
| proxyclip-proxy-attention-improves-clip-for | 83.3 |
| denseclip-extract-free-dense-labels-from-clip | 74.9 |
| learning-to-generate-text-grounded-mask-for | 83.2 |
| groupvit-semantic-segmentation-emerges-from | 79.7 |
| harnessing-vision-foundation-models-for-high | 88.7 |
| tagalign-improving-vision-language-alignment | 87.9 |
| cosmos-cross-modality-self-distillation-for | 77.7 |
| reco-retrieve-and-co-segment-for-zero-shot-1 | 57.7 |