FREDOM - DeepLabV2

Reported on 2 benchmarks across 1 task · 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· 2023-04-04
59.1
best: 78.1 (HALO)
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding arXiv:2304.02135
Domain AdaptationonGTA5 to Cityscapes
mIoU· 2023-04-04
61.3
best: 77.8 (HALO)
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding arXiv:2304.02135