Unsupervised Semantic Segmentation With 9
Metriken
mIoU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | mIoU |
|---|---|
| denseclip-extract-free-dense-labels-from-clip | 16.4 |
| learning-to-generate-text-grounded-mask-for | 22.4 |
| ttd-text-tag-self-distillation-enhancing | 19.4 |
| cosmos-cross-modality-self-distillation-for | 23.2 |
| tagalign-improving-vision-language-alignment | 25.3 |
| reco-retrieve-and-co-segment-for-zero-shot-1 | 14.8 |
| harnessing-vision-foundation-models-for-high | 28.6 |
| ttd-text-tag-self-distillation-enhancing | 23.7 |
| proxyclip-proxy-attention-improves-clip-for | 26.8 |
| groupvit-semantic-segmentation-emerges-from | 11.1 |