Open Vocabulary Semantic Segmentation On 5
평가 지표
mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | mIoU |
|---|---|
| learning-to-generate-text-grounded-mask-for | 83.2 |
| maskclip-a-mask-based-clip-fine-tuning | 96.8 |
| open-vocabulary-segmentation-with-semantic | 97.2 |
| prompt-pre-training-with-twenty-thousand-1 | 89.4 |
| open-vocabulary-semantic-segmentation-with | 94.5 |
| open-vocabulary-semantic-segmentation-with-4 | 96.4 |
| open-vocabulary-panoptic-segmentation-with-1 | 84.6 |
| decoupling-zero-shot-semantic-segmentation | - |
| tagalign-improving-vision-language-alignment | 87.9 |
| 2112-14757 | - |
| learning-mask-aware-clip-representations-for | 92.1 |
| open-vocabulary-semantic-segmentation-with-2 | 72.3 |
| hyperseg-towards-universal-visual | 92.1 |
| collaborative-vision-text-representation | 96.5 |
| in-defense-of-lazy-visual-grounding-for-open | 82.5 |
| silc-improving-vision-language-pretraining | 97.6 |
| convolutions-die-hard-open-vocabulary-1 | 95.4 |
| cat-seg-cost-aggregation-for-open-vocabulary | 97.0 |
| 모델 19 | 92.1 |