Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/HRDA+PiPa

HRDA+PiPa

Reported on 11 benchmarks across 4 tasks · 1 paper · 8 SOTA

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

Computer Vision3 results

Image-to-Image TranslationonSYNTHIA-to-Cityscapes
MIoU (13 classes)· 2022-11-14
74.8
best: 75.9 (DCF)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609
Image-to-Image TranslationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2022-11-14
68.2
best: 69.3 (DCF)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609
Image-to-Image TranslationonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
75.6
best: 77.7 (DCF)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609

Medical3 results

Image GenerationonSYNTHIA-to-Cityscapes
MIoU (13 classes)· 2022-11-14
74.8
best: 75.9 (DCF)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609
Image GenerationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2022-11-14
68.2
best: 69.3 (DCF)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609
Image GenerationonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
75.6
best: 77.7 (DCF)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609

Miscellaneous3 results

1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
MIoU (13 classes)· 2022-11-14
74.8
best: 75.9 (DCF)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609
1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2022-11-14
68.2
best: 69.3 (DCF)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609
1 Image, 2*2 StitchingonGTAV-to-Cityscapes Labels
mIoU· 2022-11-14
75.6
best: 77.7 (DCF)
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609

Methodology2 results

Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU· 2022-11-14
68.2
best: 78.1 (HALO)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609
Domain AdaptationonGTA5 to Cityscapes
mIoU· 2022-11-14
75.6
best: 77.8 (HALO)
SOTA
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation arXiv:2211.07609