Unsupervised Domain Adaptation Using Approximate Label Matching
Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target distribution. In this work, we present approximate label matching (ALM), a new unsupervised domain adaptation technique that creates and leverages a rough labeling on the test samples, then uses these noisy labels to learn a transformation that aligns the source and target samples. We show that the transformation estimated by ALM has favorable properties compared to transformations estimated by other methods, which do not use any kind of target labeling. Our model is regularized by requiring that a classifier trained to discriminate source from transformed target samples cannot distinguish between the two. We experiment with ALM on simulated and real data, and show that it outperforms techniques commonly used in the field.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reduc…
Domain AdaptationUnsupervised Domain AdaptationPreserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks
Unsupervised domain adaptation seeks to mitigate the distribution discrepancy between source and target domains, given labeled samples of the source domain and unlabeled samples of the target domain. Generative adversari…
Domain AdaptationGenerative Adversarial NetworkUnsupervised Domain AdaptationHoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
Minimizing the discrepancy of feature distributions between different domains is one of the most promising directions in unsupervised domain adaptation. From the perspective of distribution matching, most existing discre…
Domain AdaptationUnsupervised Domain AdaptationCo-regularized Alignment for Unsupervised Domain Adaptation
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred …
Domain AdaptationUnsupervised Domain AdaptationMV-Match: Multi-View Matching for Domain-Adaptive Identification of Plant Nutrient Deficiencies
An early, non-invasive, and on-site detection of nutrient deficiencies is critical to enable timely actions to prevent major losses of crops caused by lack of nutrients. While acquiring labeled data is very expensive, co…
Domain AdaptationUnsupervised Domain Adaptation