DRO (Resnet-18)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Methodology2 results

Domain AdaptationonNICO Vehicle
Accuracy· 2019-11-20
77.61
best: 81.59 (NAS-OoD)
SOTA
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization arXiv:1911.08731
Domain AdaptationonNICO Animal
Accuracy· 2019-11-20
77.61
best: 88.72 (NAS-OoD)
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization arXiv:1911.08731

Computer Vision2 results

Domain GeneralizationonNICO Vehicle
Accuracy· 2019-11-20
77.61
best: 81.59 (NAS-OoD)
SOTA
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization arXiv:1911.08731
Domain GeneralizationonNICO Animal
Accuracy· 2019-11-20
77.61
best: 88.72 (NAS-OoD)
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization arXiv:1911.08731