Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
This addresses a more realistic and challenging setting for domain adaptation, where acquiring clean labeled data is difficult, but it is incremental as it builds on existing UDA methods.
The paper tackles the problem of unsupervised domain adaptation with noisy labeled source data, proposing the Butterfly framework to handle noisy-to-clean, labeled-to-unlabeled, and source-to-target distributional adaptations, and shows it significantly outperforms baseline methods.
In unsupervised domain adaptation (UDA), classifiers for the target domain (TD) are trained with clean labeled data from the source domain (SD) and unlabeled data from TD. However, in the wild, it is difficult to acquire a large amount of perfectly clean labeled data in SD given limited budget. 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). We show that WUDA ruins all UDA methods if taking no care of label noise in SD, and to this end, we propose a Butterfly framework, a powerful and efficient solution to WUDA. Butterfly maintains four deep networks simultaneously, where two take care of all adaptations (i.e., noisy-to-clean, labeled-to-unlabeled, and SD-to-TD-distributional) and then the other two can focus on classification in TD. As a consequence, Butterfly possesses all the conceptually necessary components for solving WUDA. Experiments demonstrate that, under WUDA, Butterfly significantly outperforms existing baseline methods.