SSRT-B (ours)

Reported on 3 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Methodology2 results

Domain AdaptationonOffice-31
Average Accuracy· 2022-04-16
93.5
best: 96 (FFTAT)
SOTA
Safe Self-Refinement for Transformer-based Domain Adaptation arXiv:2204.07683
Domain AdaptationonVisDA2017
Accuracy· 2022-04-16
88.76
best: 93.8 (FFTAT)
SOTA
Safe Self-Refinement for Transformer-based Domain Adaptation arXiv:2204.07683

Other1 result

Unsupervised Domain AdaptationonVisDA2017
Accuracy· 2022-04-16
88.76
best: 93.8 (FFTAT)
SOTA
Safe Self-Refinement for Transformer-based Domain Adaptation arXiv:2204.07683