BiMaL

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Methodology2 results

Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU· 2021-08-06
46.2
best: 78.1 (HALO)
BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation arXiv:2108.03267
Domain AdaptationonGTAV-to-Cityscapes Labels
mIoU· 2021-08-06
47.3
best: 75.9 (MIC)
BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation arXiv:2108.03267

Other1 result

Unsupervised Domain AdaptationonGTAV-to-Cityscapes Labels
mIoU· 2021-08-06
47.3
best: 75.9 (MIC)
BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation arXiv:2108.03267