Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
This addresses the challenge of high data collection costs in domain adaptation for machine learning practitioners, though it is incremental as it builds on existing UDA methods.
The paper tackles the problem of unsupervised domain adaptation with limited budget by introducing a setting where classifiers are trained using complementary-label data from the source domain instead of fully-true-label data, and proposes CLARINET, which significantly outperforms baselines in experiments.
In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, the complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.