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/Sepico + HIAST

Sepico + HIAST

Reported on 14 benchmarks across 5 tasks · 1 paper · 2 SOTA

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

Methodology3 results

Domain AdaptationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2023-02-14
59.6
best: 69.3 (DCF)
SOTA
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
Domain AdaptationonGTA5 to Cityscapes
mIoU· 2023-02-14
64.1
best: 77.8 (HALO)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2023-02-14
68.1
best: 75.9 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992

Computer Vision3 results

Image-to-Image TranslationonGTAV-to-Cityscapes Labels
mIoU· 2023-02-14
64.1
best: 77.7 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
Image-to-Image TranslationonSYNTHIA-to-Cityscapes
MIoU (13 classes)· 2023-02-14
68.1
best: 75.9 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
Image-to-Image TranslationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2023-02-14
59.6
best: 69.3 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992

Medical3 results

Image GenerationonGTAV-to-Cityscapes Labels
mIoU· 2023-02-14
64.1
best: 77.7 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
Image GenerationonSYNTHIA-to-Cityscapes
MIoU (13 classes)· 2023-02-14
68.1
best: 75.9 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
Image GenerationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2023-02-14
59.6
best: 69.3 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992

Miscellaneous3 results

1 Image, 2*2 StitchingonGTAV-to-Cityscapes Labels
mIoU· 2023-02-14
64.1
best: 77.7 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
MIoU (13 classes)· 2023-02-14
68.1
best: 75.9 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2023-02-14
59.6
best: 69.3 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992

Other2 results

Unsupervised Domain AdaptationonSYNTHIA-to-Cityscapes
MIoU (16 classes)· 2023-02-14
59.6
best: 69.3 (DCF)
SOTA
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992
Unsupervised Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2023-02-14
68.1
best: 75.9 (DCF)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation arXiv:2302.06992