Wildly Unsupervised Domain Adaptation and Its Powerful and Efficient Solution
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 hard 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 models (e.g., 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationUnsupervised Domain AdaptationWildly Unsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
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…
Domain AdaptationUnsupervised Domain AdaptationWildly Unsupervised Domain AdaptationDeep Discriminative Learning for Unsupervised Domain Adaptation
The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled ta…
Domain AdaptationGeneral Classificationimage-classificationImage Classification+3Deep CORAL: Correlation Alignment for Deep Domain Adaptation
Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms …
Domain AdaptationDomain GeneralizationImage ClassificationUnsupervised Domain AdaptationA Survey of Unsupervised Deep Domain Adaptation
Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distributi…
Domain AdaptationSurveyTransfer LearningUnsupervised Domain AdaptationUnsupervised Domain Adaptation for MRI Volume Segmentation and Classification Using Image-to-Image Translation
Unsupervised domain adaptation is a type of domain adaptation and exploits labeled data from the source domain and unlabeled data from the target one. In the Cross-Modality Domain Adaptation for Medical Image Segmenta-ti…
Domain AdaptationImage-to-Image TranslationSegmentationUnsupervised Domain Adaptation