Wildly Unsupervised Domain Adaptation

1 papers with code • 4 benchmarks • 1 datasets

Transferring knowledge from a noisy source domain to unlabeled target domain.

Most implemented papers

Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation

fengliu90/Butterfly 19 May 2019

Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA).