Unsupervised Semantic Segmentation With 2
المقاييس
mIoU
pixel accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
اسم النموذج | mIoU | pixel accuracy | Paper Title | Repository |
|---|---|---|---|---|
| DenseCLIP | 15.3 | 34.1 | Extract Free Dense Labels from CLIP | |
| ReCo | 29.8 | 70.6 | ReCo: Retrieve and Co-segment for Zero-shot Transfer | - |
| ReCo+ | 31.9 | 75.3 | ReCo: Retrieve and Co-segment for Zero-shot Transfer | - |
0 of 3 row(s) selected.