DAFormer + PiPa

Reported on 5 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision1 result

Image-to-Image TranslationonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
71.7
best: 77.7 (DCF)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609

Methodology1 result

Domain AdaptationonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
71.7
best: 75.9 (MIC)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609

Medical1 result

Image GenerationonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
71.7
best: 77.7 (DCF)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609

Other1 result

Unsupervised Domain AdaptationonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
71.7
best: 75.9 (MIC)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609

Miscellaneous1 result

1 Image, 2*2 StitchingonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
71.7
best: 77.7 (DCF)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609