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/DAFormer + ProCST

DAFormer + ProCST

Reported on 19 benchmarks across 7 tasks · 1 paper

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

Medical6 results

Image GenerationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· uses extra data· 2022-04-25
68.2
best: 74.8 (HRDA + PiPa)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Image GenerationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 77.7 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Image GenerationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 77.7 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Image GenerationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· uses extra data· 2022-04-25
61.6
best: 69.3 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Semantic SegmentationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 75.9 (MIC)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Semantic SegmentationonSYNTHIA-to-Cityscapes
Mean IoU· uses extra data· 2022-04-25
61.6
best: 68.2 (HRDA + PiPa)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891

Computer Vision4 results

Image-to-Image TranslationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· uses extra data· 2022-04-25
68.2
best: 74.8 (HRDA + PiPa)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Image-to-Image TranslationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 77.7 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Image-to-Image TranslationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 77.7 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Image-to-Image TranslationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· uses extra data· 2022-04-25
61.6
best: 69.3 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891

Methodology4 results

Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU· uses extra data· 2022-04-25
61.6
best: 78.1 (HALO)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Domain AdaptationonGTA5 to Cityscapes
mIoU· uses extra data· 2022-04-25
69.4
best: 77.8 (HALO)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Domain AdaptationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 75.9 (MIC)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· uses extra data· 2022-04-25
68.2
best: 75.9 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891

Miscellaneous4 results

1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
mIoU (13 classes)· uses extra data· 2022-04-25
68.2
best: 74.8 (HRDA + PiPa)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
1 Image, 2*2 StitchingonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 77.7 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
1 Image, 2*2 StitchingonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 77.7 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
MIoU (16 classes)· uses extra data· 2022-04-25
61.6
best: 69.3 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891

Other2 results

Unsupervised Domain AdaptationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 75.9 (MIC)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
Unsupervised Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· uses extra data· 2022-04-25
68.2
best: 75.9 (DCF)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891

Audio2 results

10-shot image generationonGTAV-to-Cityscapes Labels
mIoU· uses extra data· 2022-04-25
69.4
best: 75.9 (MIC)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891
10-shot image generationonSYNTHIA-to-Cityscapes
Mean IoU· uses extra data· 2022-04-25
61.6
best: 68.2 (HRDA + PiPa)
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer arXiv:2204.11891